item: #1 of 872 id: fcis-10198 author: Kang, Yunfeng; Mai, Yixin title: Robot Motion Planning with Optimization-based Algorithm and Neural Network: Unsupervised Path Regression date: 2023 words: 3878 flesch: 61 summary: References [1] S. M. LaValle et al., “Rapidly-exploring random trees: A new tool for path planning,” 1998. [2] L. E. Kavraki, P. Svestka, J.-C. Latombe, and M. H. Overmars, “Probabilistic roadmaps for path planning in high-dimensional configuration spaces,” IEEE transactions on Robotics and Automation, vol. 12, no. 4, pp. 566–580, 1996. keywords: fig; motion; network; path; planning; robot; world cache: fcis-10198.pdf plain text: fcis-10198.txt item: #2 of 872 id: fcis-10203 author: Zhao, Tian title: A Question Answering System for Situation Puzzle with SPQA date: 2023 words: 3645 flesch: 70 summary: In SPQA model, the “unseen” dataset only includes “yes/no questions” format datasets. On this metric, all the numbers are only above 10%, which demonstrates that SPQA models generally don’t causes better performance on all yes/no QA datasets. keywords: datasets; model; puzzle; situation; spqa; tuning; unifiedqa cache: fcis-10203.pdf plain text: fcis-10203.txt item: #3 of 872 id: fcis-10208 author: Lu, Hongwei title: LSTM-Based Stock Price Prediction date: 2023 words: 2299 flesch: 62 summary: In view of the high noise, nonlinearity and non-stationarity of stock price data, which makes it very difficult to accurately predict the stock price, this paper intends to use the long-short-term memory network (Long Short-Term Memory, LSTM) In the end, the optimization of the model based on the method of deep learning, and the attempt to improve the prediction accuracy of the model by fusing stock data from different sources are elaborated in detail. keywords: data; gate; information; layer; lstm; stock cache: fcis-10208.pdf plain text: fcis-10208.txt item: #4 of 872 id: fcis-10209 author: Zhang, Jun title: Weed Recognition Method based on Hybrid CNN-Transformer Model date: 2023 words: 4346 flesch: 46 summary: There algorithms not only have the ability to automatically extract features from weed images, but also achieve higher recognition accuracy and real-time performance. These algorithms can not only automatically extract features from weed images, but also have higher recognition accuracy and real-time performance[5]. keywords: accuracy; cnn; extraction; features; hybrid; learning; model; performance; recognition; transformer; weed cache: fcis-10209.pdf plain text: fcis-10209.txt item: #5 of 872 id: fcis-10210 author: Gong, Jie; Li, Ming title: Design of Multi-circuit Motor Control System based on Fabric Defect Detection Device date: 2023 words: 2404 flesch: 52 summary: The industry has improved the performance and real-time processing speed of the control system to handle complex data by combining various different high-performance processors with the lower computer, such as the ARM and microcontroller based electrochemical analyzer designed by Paulraj Santharaman et al[1]-[5], where ARM is used as the central control to realize the control system design through parallel bus and rich peripheral interfaces, E.B. Kapisch et al. designed ARM and FPGA based power system recorder[6]-[10], using field programmable gate array (FPGA) and ARM platform and other devices to process EPS signals in an intelligent way, the above different systems have the advantages of parallel control, scalability and computing performance over the control system, but this architecture requires complex underlying hardware, and the data between ARM and microcontroller, CPLD, FPGA CPLD, FPGA data transfer between the slow, unstable, not suitable for motor control such as real-time demanding scenarios. 3. FPGA Implementation FPGA is the key of the whole motor control system, responsible for the reception of communication data, data caching, data cyclic output, motor drive control circuit, etc. keywords: chip; control; data; drive; fpga; module; motor; system; time cache: fcis-10210.pdf plain text: fcis-10210.txt item: #6 of 872 id: fcis-10301 author: Li , Anqian; Kang, Baoyuan; Huo, Yuyan; Zuo, Xinyu; Niu, Shufang title: Analysis and Improvement on a Three-Factor Authentication Scheme in IoT Environment date: 2023 words: 6600 flesch: 77 summary: Nj chooses IDj, jr ,and computes ( || || )j GN j jMP h K r ID , ( || )j j j GNMI r h ID K  , where GUK is the shared key between GW and Nj. *( || || || )j j j keywords: authentication; j j; mni; scheme; || || cache: fcis-10301.pdf plain text: fcis-10301.txt item: #7 of 872 id: fcis-10302 author: Wang, Zhaolian; Huang, Hong; Du, Rui; Li, Xing; Yuan, Guotao title: IoT Intrusion Detection Model based on CNN-GRU date: 2023 words: 4251 flesch: 54 summary: In the exploration of IoT intrusion detection models, several methods and techniques have been proposed by researchers. To reduce data, feature redundancy during the identification process, this study proposes the use of Extreme Gradient Boosting (XGBoost) for feature selection to obtain an optimal feature subset. keywords: accuracy; cnn; dataset; detection; feature; gru; intrusion; iot; layer; model; traffic cache: fcis-10302.pdf plain text: fcis-10302.txt item: #8 of 872 id: fcis-10303 author: Rong, Lihui title: Application of Smart Site Construction Technology based on BIM Technology date: 2023 words: 2293 flesch: 35 summary: In the smart site construction project, the application effect of BIM technology can not only improve the construction quality of the project, but also optimize the application effect of smart site construction technology while reducing the difficulty. Government departments have paid great attention to quality issues in the construction stage of construction projects, and with the strong support of the government, with the continuous development of the construction industry, it has provided extensive spatial support for the application of BIM technology. keywords: application; bim; construction; project; site; technology cache: fcis-10303.pdf plain text: fcis-10303.txt item: #9 of 872 id: fcis-10304 author: Deng, Pengfei; Liang, Xiyin; Pan, Peirong; Pan, Xu title: Overview of System-Level Security Technologies based on ARM TrustZone date: 2023 words: 3813 flesch: 39 summary: In short, in the protection of system security isolation technology has become a trend, to a certain extent, to break the bottleneck of the current system security, it has become an important system security technology. At the same time, to improve system security based on ARM TrustZone technology, it is necessary to make corresponding extensions to the system hardware and processor cores. keywords: arm; environment; execution; hardware; isolation; security; system; technology; tee; trustzone cache: fcis-10304.pdf plain text: fcis-10304.txt item: #10 of 872 id: fcis-10305 author: Zuo, Xinyu; Wang, Zhangang; Li, Anqian; Huo, Yuyan; Niu, Shufang title: Analysis and Improvement of PUF-based Secure Anonymous User Authentication Scheme in Smart Home Environment date: 2023 words: 5438 flesch: 80 summary: In recent years, with the popularity of IoT applications, scholars have proposed many authentication schemes for smart home environment [14] Naoui S, Elhdhili M E, Saidane L A. Lightweight and secure password based smart home authentication protocol: LSP- SHAP. keywords: authentication; h h; scheme;  ;   cache: fcis-10305.pdf plain text: fcis-10305.txt item: #11 of 872 id: fcis-10367 author: Meng, Qianhui; Sun, Ruikang title: Visual Analysis of Campus Card Consumption Data based on Matplotlib: -- Anhui University of Finance and Economics as an Example date: 2023 words: 3314 flesch: 48 summary: We continued the analysis of student consumption data in the dining category based on the number of card swipes. Subsequently, the Matplotlib library was utilized to visually analyze both overall data of student consumption and the dining data with its higher proportion. keywords: analysis; cafeteria; campus; card; consumption; data; dining; school; students cache: fcis-10367.pdf plain text: fcis-10367.txt item: #12 of 872 id: fcis-10368 author: Luo, Guang title: Calculation of Required Air Volume and Verification of Ventilation Capacity for Mines date: 2023 words: 3241 flesch: 57 summary: The excavation working faces in Xinyuan Coal Mine that require air volume calculation include the southern section of 11211 air tunnel, 11211 air tunnel, 21903 machine tunnel small system, 21903 machine tunnel small system, 12210 machine tunnel, 12213 air tunnel, and 12213 machine tunnels, all of which are semi coal rock tunnels. Calculation results of required air volume for excavation working face (Unit: m3/min) Calculation basis 11211Wind lane south section 11211 Wind alley 21903 Machine Lane small system 21903 Air Lane small system 12210 Machine Lane 12213 Wind tunnel 12213 Machine Lane Total Gas emission 122.4 82.8 19.2 28.8 64.8 128.4 129.6 576 Carbon dioxide emission 4.02 4.02 4.02 4.02 4.02 4.02 4.02 28.14 Actual suction volume of local ventilation fan 743.9 615.3 389 665.2 804.6 766.6 837.3 4821.9 Number of staff 120 120 120 120 120 120 120 840 Wind speed verification 237.9~3806.4 234.3~3748.8 262.4~4197.6 262.4~4197.6 267.6~4281.6 234.6~3753.6 237.3~3796.8 - Maximum value 743.9 615.3 389 665.2 804.6 766.6 837.3 4821.9 2.3. keywords: air; coal; face; min; mining; ventilation; volume cache: fcis-10368.pdf plain text: fcis-10368.txt item: #13 of 872 id: fcis-10369 author: Li, Xin; Huang, Hong; Yuan, Guotao; Wang, Zhaolian; Du, Rui title: An Intrusion Detection Method based on Fusion Neural Network date: 2023 words: 4930 flesch: 49 summary: UNSW-NB15 contains a wider range of attack types and network traffic features, allowing for a more comprehensive evaluation of intrusion detection models. Insufficient feature learning from the minority class samples leads to lower detection rates for these classes, which affects the performance of intrusion detection models and may result in highly threatening attack behaviors being misclassified as normal behavior, thereby adversely affecting the devices. keywords: class; data; dataset; detection; features; intrusion; learning; model; msff; network; performance; scale cache: fcis-10369.pdf plain text: fcis-10369.txt item: #14 of 872 id: fcis-10370 author: Song, Zhen; Deng, Hongwei title: Research on Sensor Optimization Technology of Driverless Vehicle date: 2023 words: 6045 flesch: 48 summary: Optimization of Anti-jamming Performance of Sensor Anti-interference is an important part of sensor detection, commonly used anti-noise, anti-electromagnetic field and other interference sources of technology mainly include shielding technology, electrostatic shielding and electromagnetic shielding. The range and accuracy of sensor perception information directly affect the subsequent decision-making level of driverless cars, and the sensor perception range is limited, the current maximum perception distance is about 250 meters, and the perception range of high-speed vehicles is shorter[41]. keywords: data; detection; development; driving; environmental; ieee; image; information; lidar; light; method; perception; research; road; sensor; technology; traffic; vehicle cache: fcis-10370.pdf plain text: fcis-10370.txt item: #15 of 872 id: fcis-10733 author: Zhang, Luyao; Cai, Lecai title: Exploration on the Construction of County Medical Community Information Platform date: 2023 words: 3439 flesch: 34 summary: Resource Sharing Utilizing existing medical resources, establish an open and shared resource sharing center within the medical community for medical testing, imaging diagnosis, electrocardiogram diagnosis, pathological diagnosis, clinical medical records, and medical data. Information Security Due to the unique nature of medical data, it is necessary to ensure its privacy, availability, and controllability. keywords: community; construction; county; data; diagnosis; health; level; medical; treatment cache: fcis-10733.pdf plain text: fcis-10733.txt item: #16 of 872 id: fcis-10735 author: Wu, Yue title: Real-time Classifier of Multilingual Font Styles based on ResNet, SwordNet, Logistic Regression and Random Forest Algorithms date: 2023 words: 4298 flesch: 64 summary: The training model is performed using the input x values (font images) and y values (labels). Training and Results The training model is performed using the input x values (font images) and y values (labels). keywords: algorithm; data; fig; font; forest; image; model; resnet; time cache: fcis-10735.pdf plain text: fcis-10735.txt item: #17 of 872 id: fcis-10736 author: Zhou, Xu; Lin, Guojun title: Review of Target Detection Algorithms date: 2023 words: 2150 flesch: 47 summary: This paper mainly introduces the traditional target detection algorithm and two kinds of target detection algorithm based on depth learning and the data set commonly used in target detection. [11] target detection algorithm has higher detection accuracy and faster detection speed than previous models. keywords: algorithm; cnn; detection; image; object; stage; target cache: fcis-10736.pdf plain text: fcis-10736.txt item: #18 of 872 id: fcis-10737 author: Huo, Yuyan; Kang, Baoyuan; Zuo, Xinyu; Niu, Shufang; Li, Anqian title: Analysis and Improvement of Authentication Schemes for Industrial Wireless Sensor Networks with Fog Computing date: 2023 words: 5838 flesch: 75 summary: In this subsection, user Ui, fog server FSj and cloud server CS authenticate each other and agree on a session key, then user Ui can communicate securely with fog server FSj. Shortcoming 3 After user Ui and fog server FSj complete a mutual authentication process, fog server FSj can obtain user Ui’s IDi, SKuc-cs and Bi by decrypting S3. keywords: cloud; fog; message; scheme; server; user cache: fcis-10737.pdf plain text: fcis-10737.txt item: #19 of 872 id: fcis-1074 author: Cheng, Yuanyuan title: Image Defogging Algorithm Based on Deblurgan Network date: 2022 words: 3294 flesch: 48 summary: [4] proposed a DehazeNet defogging network to estimate the transmittance in the atmospheric model, pioneering the use of neural networks for image defogging; Zhang The generator G generates sample data that approximates the real data by learning the input data, and the input has fog images and directly outputs fog-free images; the role of discriminator D is to distinguish the real data from the samples generated by the generator G. keywords: algorithm; conv; convolution; defogging; discriminator; generator; image; loss; network; relu cache: fcis-1074.pdf plain text: fcis-1074.txt item: #20 of 872 id: fcis-1075 author: Liu, Qinfeng; Liu, Hui; Wang, Tao; Zhang, Enke title: Research and application of mobile workbench for clinical medical engineers in hospital date: 2022 words: 3123 flesch: 36 summary: The mobile workbench system connects with the database of the hospital's equipment asset management system, equipment maintenance management system and consumables asset management system to realize the whole process tracking management of medical equipment and consumables from admission to abandonment, including acceptance, warehousing, repair, maintenance, regular inspection, disinfection and sterilization, and scrapping. Frontiers in Computing and Intelligent Systems ISSN: 2832-6024 | Vol. 1, No. 1, 2022 9 Research and application of mobile workbench for clinical medical engineers in hospital Qinfeng Liu1, Hui Liu1, Tao Wang2, *, Enke Zhang1 1 Medical Equipment Management Department, Shaanxi Provincial People 's Hospital, Xi’an Shaanxi 710068, China; 2 Department of Medical Imaging, Hospital of Stomatology, Xi’an Jiaotong University, Xi’an Shaanxi 710004, keywords: engineers; equipment; hospital; maintenance; management; rate; system; wireless; workbench cache: fcis-1075.pdf plain text: fcis-1075.txt item: #21 of 872 id: fcis-1076 author: Lu, Qiduo; Ye, Xia; Zhu, Chenhao title: Research on Multimodal Summarization Based on Sequence to Sequence Model date: 2022 words: 3503 flesch: 46 summary: Although multimodal attention shows great potential in the task of text image summarization, it is not enough to complete the task of text video audio summarization by itself. In order to integrate multimodal information more effectively and give full play to the interaction and complementarity of modal information, we should consider a more appropriate architecture based on the current architecture. keywords: attention; data; image; information; model; multimodal; sequence; summarization; text cache: fcis-1076.pdf plain text: fcis-1076.txt item: #22 of 872 id: fcis-10765 author: Wei , Zihe title: Fire Detection of yolov8 Model based on Integrated SE Attention Mechanism date: 2023 words: 1654 flesch: 51 summary: The mAP@0.5 is a widely used metric for evaluating the performance of object detection models. Overall, our model has great potential for detecting fires and other image recognition tasks, improving the accuracy and speed of fire detection systems, and ultimately reducing the risk and impact of fires. keywords: attention; detection; mechanism; model cache: fcis-10765.pdf plain text: fcis-10765.txt item: #23 of 872 id: fcis-10766 author: Fang, Liwei title: Study on Health and Comfort in Buildings based on Home Thermal Comfort Survey date: 2023 words: 1563 flesch: 56 summary: Using advanced cool materials in the urban built environment to mitigate heat islands and improve thermal comfort conditions. Consequently, the room temperature went up together with internal absolute humidity although outside condition reduced. keywords: comfort; figure; temperature; window cache: fcis-10766.pdf plain text: fcis-10766.txt item: #24 of 872 id: fcis-10850 author: Zheng, Siyi title: Design and Implementation of a Small Program for Collecting Ethnic Voice date: 2023 words: 2774 flesch: 56 summary: Language researchers can share their voice data with other users or research institutions to promote language research and protection. Audio corpora and annotation information can be shared with other users or research institutions to promote language research and protection. keywords: audio; corpus; language; mini; recording; system; table; user; wechat cache: fcis-10850.pdf plain text: fcis-10850.txt item: #25 of 872 id: fcis-10851 author: Chen, Xingxing title: QT and Simulink Mixed Call Implementation date: 2023 words: 1365 flesch: 55 summary: Therefore, the interface implementation of mixed programming between Qt and Simulink is of great significance to the whole project. Qt Works 1.Create a project in Qt that imports the code generated in simulink Fig 10. keywords: code; fig; simulink cache: fcis-10851.pdf plain text: fcis-10851.txt item: #26 of 872 id: fcis-1089 author: Zhang, Zijie; Zeng, Jing title: A Survey on Visual Simultaneously Localization and Mapping date: 2022 words: 3116 flesch: 57 summary: This paper introduces the development of visual Slam at home and abroad, the basic methods of visual slam, and the key problems in visual slam, and discusses the main development trends and research hotspots of visual slam. According to the number and category of cameras, visual slam can be divided into monocular slam, stereoscopic slam, RGB-D slam keywords: feature; frame; image; key; map; method; pose; slam; time cache: fcis-1089.pdf plain text: fcis-1089.txt item: #27 of 872 id: fcis-1100 author: Jing, Hongrong; Lin, Guojun; Zhang, Hongjie; Chen, Tiantian title: A Face Recognition Algorithm Based on Improved Resnet date: 2022 words: 2710 flesch: 59 summary: Experiments on LFW and AgeDB data sets show that the algorithm can not only learn deep-face characteristics but also efficiently improve the accuracy of face recognition compared with ordinary CNN. Keywords: Deep learning; Residual; Face recognition; Softmax; Improved loss function. keywords: accuracy; deep; face; function; loss; network; recognition cache: fcis-1100.pdf plain text: fcis-1100.txt item: #28 of 872 id: fcis-11018 author: Zhao, Zexin title: Abnormal Behavior Fish and Population Detection Method based on Deep Learning date: 2023 words: 3529 flesch: 54 summary: Since machine learning methods for fish detection in underwater images are inexpensive and easy to operate, Therefore, it has been widely used in fish species detection Abnormal fish behavior reflects fish disease and changes in water environment. keywords: algorithm; behavior; chinese; data; detection; fish; method; model; object; target; yolov8 cache: fcis-11018.pdf plain text: fcis-11018.txt item: #29 of 872 id: fcis-11132 author: Ma, Lijun; Zhu, He; Xu, Xiaojian; Xing, Yanxia; Li, Bo; Yu, Yang; Zhu, Mengliu title: System Design of Microcrystal Freezing Sleeping Equipment and Research on Effect of Foie Gras Fast Cooling Equipment date: 2023 words: 5404 flesch: 56 summary: There was no significant difference between the tenderness of foie gras treated by microcrystalline freezing device and that of fresh meat group. As a result, foie gras frozen before thawed may be more difficult to chew and digest than fresh foie gras, and can vary in taste and texture. keywords: difference; equipment; foie; freezing; gras; group; heat; instrument; liquid; meat; nitrogen; rate; technology; temperature; time cache: fcis-11132.pdf plain text: fcis-11132.txt item: #30 of 872 id: fcis-11134 author: Gao, Jiaxin; Chen, Yuelu; Cao, Baolong; Chen, Yiming; Li, Chuanqi title: Training Scene Construction and Motion Realization of Unmanned Craft based on Unreal Engine date: 2023 words: 4320 flesch: 50 summary: The method makes full use of Unreal Engine's powerful graphic rendering ability and physics engine function, and combines 3D MAX to realize the rapid construction of unmanned craft training scene, environment simulation, and unmanned craft motion simulation and control. The method uses the powerful graphic rendering ability of Unreal engine to realize the rapid modeling of real terrain and environment simulation, which can meet the needs of unmanned craft training on terrain and navigation environment, and does not need to occupy the relevant site or wait for special weather. keywords: cos; cos cos; cos sin; craft; engine; simulation; sin sin; training;   cache: fcis-11134.pdf plain text: fcis-11134.txt item: #31 of 872 id: fcis-11135 author: Lu, Jingxuan; Jeong, YangKwon; Xue, Jiaqi title: Design and Implementation of a Learning Resource Recommendation System based on User Habits Based on GNN date: 2023 words: 2512 flesch: 43 summary: Finally, the system should ensure the security and privacy of user data to avoid the leakage or abuse of user information. Combined with user habit features, appropriate recommendation algorithms are employed to recommend learning resources that align with their interests and habits. keywords: data; graph; learning; recommendation; system; users cache: fcis-11135.pdf plain text: fcis-11135.txt item: #32 of 872 id: fcis-11136 author: Zhong, Shuming; Jiang, Hongyu; Zhao, Haihong title: Design and Development of APP based on Android Vision Testing and Protection date: 2023 words: 4738 flesch: 52 summary: Using the touch-screen sensing feature, the phone can intelligently determine and test the visual acuity by simply swiping left and right on the screen according to the opening direction of the letter E, up, down, 21 Eyes relaxing and focusing for visual training Eyes relaxing and focusing for visual acuity test on the National Eye Care Day. Vision test APP test vision is simple and convenient, but also can generate care recommendations, you can detect problems in time, to prevent eyesight continue to decline. keywords: acuity; blindness; color; eye; eyes; method; myopia; people; shiyong; software; test; vision; zheng cache: fcis-11136.pdf plain text: fcis-11136.txt item: #33 of 872 id: fcis-11146 author: Li, Xueguang; Dumlao, Menchita F. title: SOC Prediction for Lithium Battery Via LSTM-Attention-R Algorithm date: 2023 words: 5562 flesch: 60 summary: [12] Xu, Z., et al., Co-estimating the state of charge and health of lithium batteries through combining a minimalist electrochemical model and an equivalent circuit model. The algorithm proposed provides a better research direction for future parameter prediction in the field of lithium batteries. keywords: algorithm; attention; battery; energy; estimation; lithium; lstm; model; network; soc; state cache: fcis-11146.pdf plain text: fcis-11146.txt item: #34 of 872 id: fcis-11147 author: He, Jiahao title: Research on Computer Network Security Prevention in the Context of Big Data date: 2023 words: 3565 flesch: 32 summary: In the context of big data, network security threats are increasing, and traditional methods of collecting and analyzing threat intelligence can no longer meet the complex and changing threat situation. Real-time and Adaptive Intelligent security monitoring and response system has the ability to monitor and respond in real-time, so that it can discover and respond to network security threats in a timely manner. keywords: analysis; data; encryption; intelligence; network; security; threat cache: fcis-11147.pdf plain text: fcis-11147.txt item: #35 of 872 id: fcis-11149 author: Fan, Bihan; Zhang, Ji title: A Review of Medical Image Segmentation Techniques date: 2023 words: 2108 flesch: 40 summary: China Abstract: Medical image segmentation is a key task in medical imaging processing. With the continuous development and in-depth research of technology, the methods and algorithms of medical image segmentation will become increasingly intelligent and precise. keywords: algorithm; image; method; region; segmentation; technology cache: fcis-11149.pdf plain text: fcis-11149.txt item: #36 of 872 id: fcis-11150 author: Yang, Bowei title: Evaluation and Analysis of Airside Economic Zone based on GIS Technology: -- Taking Daxing Airport as an Example date: 2023 words: 2267 flesch: 43 summary: Selection and Construction of Evaluation Indicators In this paper, six indicators, namely road network density, population density, number of bus stops, transit coverage, degree of land development and information entropy of POIs, are selected. However, if the degree of land development is too low, it will lead to a waste of land resources; while if the development intensity is too high, it will make the land carrying capacity too large, which is not conducive to human health and sustainable development of the society. keywords: airport; area; development; land; road; transportation cache: fcis-11150.pdf plain text: fcis-11150.txt item: #37 of 872 id: fcis-11153 author: Xu, Kaihao title: Survey of AR Object Tracking Technology Based on Deep Learning date: 2023 words: 3363 flesch: 51 summary: As used to develop object tracking algorithms for AR applications. Discriminative methods are more robust and gradually occupy the mainstream position in object tracking algorithms. keywords: algorithms; learning; object; pose; target; technology; time; tracking cache: fcis-11153.pdf plain text: fcis-11153.txt item: #38 of 872 id: fcis-11154 author: Xu, Minghong title: Application of Improved Immune Particle Swarm Optimization in 3D Node Localization date: 2023 words: 2663 flesch: 45 summary: xmh2028410256@163.com Abstract: When 2D localization algorithm is extended to 3D space, it achieves node localization with better localization accuracy. An improved immune particle swarm optimization (IIPSO) localization algorithm is proposed to estimate the localization of nodes in wireless sensor networks (WSN). keywords: algorithm; localization; max; node; particle; positioning; search; sensor cache: fcis-11154.pdf plain text: fcis-11154.txt item: #39 of 872 id: fcis-11155 author: Yang, Huohai; Liao, Qingrong title: Well Testing Analysis Method and Practice for Low Permeability Gas Reservoirs date: 2023 words: 2925 flesch: 51 summary: Division of Flow Stages Based on the calculated typical inclined well pressure of fractured and vuggy reservoirs, and based on the characteristics of the bottomhole dimensionless pressure and its derivative curve, the well testing curve is divided into 8 flow stages: the wellbore storage effect stage (Stage I), which reflects the flow characteristics of crude oil in the wellbore during the initial well opening period, has a derivative curve slope of 1; The skin effect stage (Stage II) reflects the pollution situation in the near wellbore area, and its derivative curve shows a hump shape; The early radial flow stage (Stage III), linear flow stage (Stage IV), and transitional flow stage (Stage V) that reflect the characteristics of inclined well seepage (Figure 6a-c) have derivative curves of horizontal, oblique, and arc lines, respectively; The derivative curves of the karst cave towards fracture flow stage (stage VI), karst cave towards matrix, and matrix towards fracture flow stage (stage VII), which reflect the fluid exchange between the triple media of the reservoir, all show a concave shape; The overall radial flow stage (Stage VIII) under infinite geological boundary conditions (Figure 6d) has a derivative curve slope of 0. Conclusion (1) The typical well testing curves of inclined wells in fractured and vuggy reservoirs are divided into 8 fluid flow stages: wellbore storage effect stage, skin effect stage, early radial flow stage, linear flow stage, transitional flow stage, karst cave to fracture channeling stage, karst cave to matrix and matrix to fracture channeling stage, and overall radial flow stage. keywords: curve; flow; karst; pressure; scale; stage; testing cache: fcis-11155.pdf plain text: fcis-11155.txt item: #40 of 872 id: fcis-11156 author: Liu, Quankai; Sang, Haifeng title: Design of Real-time Pedestrian Trajectory Prediction System based on Jetson Xavier date: 2023 words: 3972 flesch: 50 summary: In the first-person view, the camera moves with the vehicle, so the vehicle's own motion is crucial for improving the accuracy of pedestrian trajectory prediction. The designed algorithm is transplanted into the embedded device Jetson Xavier to realize the whole process and real-time operation from pedestrian detection, pedestrian tracking, pedestrian attitude estimation, pedestrian optical flow estimation, pedestrian trajectory acquisition to pedestrian trajectory prediction, vehicle control, etc. keywords: algorithm; conference; features; flow; ieee; information; network; pedestrian; pose; prediction; system; trajectory cache: fcis-11156.pdf plain text: fcis-11156.txt item: #41 of 872 id: fcis-11236 author: Zheng, Chaoliang title: Web-based Financial Accounting Information Intelligent Management Platform Construction date: 2023 words: 2358 flesch: 17 summary: Financial accounting information management is different from ordinary information management, there is a certain degree of specificity, which often needs to be based on the type and quantity of financial accounting information, accounting for the overall size of the intelligent management, therefore, in the design of the financial accounting information intelligent management platform, this paper divides a number of modules and function points, set up a separate responsibility board, try to improve the connectivity of the various modules of the platform. Finally, the operational feasibility, that is, on the basis of Window to build the financial accounting information intelligent management interface and management window, analyse the security risks that exist in the management process, to fundamentally reduce the risk of financial accounting information management, according to the above analysis of the platform's intelligent management needs, you can design a reasonable BPNN financial intelligent management model, in the conventional management conditions, the selection of the standard value of financial processing. keywords: accounting; accounting information; information; management; management platform; platform cache: fcis-11236.pdf plain text: fcis-11236.txt item: #42 of 872 id: fcis-11237 author: Wu, Zidong title: Machine Learning based Data Analysis for Wordle Game date: 2023 words: 2756 flesch: 63 summary: Model Comparison Analysis and Questions and Answers By comparing the training and validation accuracies of ARIMA model and LSTM model, we understand that LSTM model gives better prediction results. In recent years, deep learning algorithms have been widely used in the field of time series forecasting models. keywords: lstm; model; prediction; results; time cache: fcis-11237.pdf plain text: fcis-11237.txt item: #43 of 872 id: fcis-11239 author: Song, Qinyu title: Research on Urban Monitoring Network Management Platform based on AI Data Stream Processing date: 2023 words: 2776 flesch: 38 summary: AI data stream processing technology refers to a technology that applies artificial intelligence (AI) algorithm to the processing and analysis of real-time data streams [10]. AI data stream processing technology has been widely used in many fields, such as financial fraud detection, intelligent traffic management, data analysis of Internet of Things, online advertising optimization, etc. keywords: data; management; monitoring; network; processing; stream; time cache: fcis-11239.pdf plain text: fcis-11239.txt item: #44 of 872 id: fcis-11254 author: Wang, Yan; Chen, Xue title: A Gravity Compensation Algorithm of Robot Manipulator Control based on the Trigonometric Function date: 2023 words: 5343 flesch: 61 summary: To verify the control effect after gravity compensation, the most easily comprehensible proportional-derivative controller combined with gravity compensation is used to control two-joint and three-joint mechanical arms for simulation. At present, some progress has been made in the study of gravity compensation, mainly including a mechanical- structure method and a control-analysis method [1]. keywords: algorithm; arm; compensation; control; g q; gravity; joint;  ;   cache: fcis-11254.pdf plain text: fcis-11254.txt item: #45 of 872 id: fcis-11266 author: Gong, Haijun title: Conference Planning and Resolution Management System date: 2023 words: 4187 flesch: 41 summary: References [1] LUO Y.A company meeting information management system [D]. MYSQL MySQL is a multi-user, multi-threaded server, using SQL database, database management system is based on SQL client as well as server model of the relationship, its advantages are powerful features, easy to operate, easy to manage, reliable and secure, faster running, multi-threaded, cross-platform, fully networked, stability, etc., is very suitable for the Web site or other application software, in database back-end development. keywords: conference; database; design; information; jsp; management; management system; meeting; system; user cache: fcis-11266.pdf plain text: fcis-11266.txt item: #46 of 872 id: fcis-11268 author: Xu, Tianyu; He, Xiaoling title: EMD-BiLSTM Stock Price Trend Forecasting Model based on Investor Sentiment date: 2023 words: 4377 flesch: 47 summary: 5. Conclusion Aiming at the problem of large prediction error caused by nonlinearity, non-stationarity and chaos of stock time series, this paper proposes a BiLSTM stock price rise and fall model based on empirical mode decomposition and investor sentiment. In order to improve the prediction accuracy, according to the temporal characteristics of stock price data, it is proposed to use a combination of empirical mode decomposition (EMD), investor sentiment and two-way long short-term memory neural network to predict the rise and fall of stock prices. keywords: data; emd; emotional; model; prediction; price; sentiment; series; stock; t t cache: fcis-11268.pdf plain text: fcis-11268.txt item: #47 of 872 id: fcis-11271 author: Xiao, Dongyang title: Key Technologies for Automatic Driving Function Implementation date: 2023 words: 2208 flesch: 49 summary: In contrast, path planning and vehicle control are dominated by classical state machines, search algorithms, and control models. Introduction Since the mid-1980s, many universities, research centers, automotive companies, and companies in other industries around the world have been researching and developing autonomous vehicles (also known as self-driving cars and driverless cars). keywords: cars; control; driving; model; planning; systems; technology; vehicle cache: fcis-11271.pdf plain text: fcis-11271.txt item: #48 of 872 id: fcis-11533 author: Mu, Juntong title: The Application and Effect of Intelligent Marketing Technology and Personalized Recommendation System in E-commerce date: 2023 words: 2267 flesch: 21 summary: By utilizing user data and intelligent algorithms, personalized recommendation systems can achieve precise recommendations, meet users' personalized needs, provide a better user experience, and promote the development of e-commerce. As personalized recommendation systems need to handle a large amount of user data, data privacy and security have become important issues. keywords: commerce; marketing; recommendation; technology; user cache: fcis-11533.pdf plain text: fcis-11533.txt item: #49 of 872 id: fcis-11534 author: Wang, Ruofei title: Verification Mechanism for Authenticity of Big Data Cloud Computing Services Based on Game Theory and Smart Contracts date: 2023 words: 3408 flesch: 40 summary: Moreover, game theory offers an effective way to study the interactions and incentive mechanisms between cloud service providers and users. Our system is composed of three main participants: users, cloud service providers, and a Trusted Third Party (TTP). keywords: cloud; computing; contract; data; providers; service; system; users; verification cache: fcis-11534.pdf plain text: fcis-11534.txt item: #50 of 872 id: fcis-11535 author: Deng, Zhiqiang; Wang, Dewen title: An Indirect Prediction Method based on Feature Extraction of Lithium-ion Batteries Remaining Useful Life date: 2023 words: 3101 flesch: 50 summary: This paper addresses the challenge of measuring battery capacity directly in real-world scenarios by employing polynomial fitting to establish a mapping between the extracted HF and battery capacity. Such a relationship indirectly reflects the extent of battery degradation. keywords: batteries; battery; capacity; lithium; lstm; model; prediction; rul cache: fcis-11535.pdf plain text: fcis-11535.txt item: #51 of 872 id: fcis-11537 author: Wang, Zi; Ren, Zheng; Li, Xue title: Identification of Coffee Leaf Pests and Diseases based on Transfer Learning and Knowledge Distillation date: 2023 words: 3243 flesch: 61 summary: In neural network model, convolution layer is used to extract image feature information [18]. However, it is difficult for lightweight models to achieve high recognition accuracy directly. keywords: accuracy; coffee; diseases; figure; image; layer; leaf; learning; method; model; network cache: fcis-11537.pdf plain text: fcis-11537.txt item: #52 of 872 id: fcis-11543 author: Chen, Jieyu; Peng, Tao; Xu, Guangcan title: Online Car Illegal Behavior Identification and Law Enforcement and Forensics Methods based on Big Data Technology date: 2023 words: 3525 flesch: 26 summary: Traditional Identification and Enforcement Methods for Illegal Online Vehicles Under the guidance of the current online vehicles management methods, China's large and medium sized cities have initially built a reasonable network reservation rental car layout, and the three regions of Beijing, Shanghai and Guangzhou have accumulated advanced experience in the regulation of online vehicles on an early and pilot basis, mainly through the identification of driver personnel information, online vehicles information identification and online vehicles insurance information and other aspects of the establishment of information databases, so as to accurately identify illegal online vehicles information. Law enforcement forensic reference elements are applied, basically realizing the intelligent management of online vehicles with history of illegal behavior and suspected illegal online vehicles. keywords: behavior; car; data; enforcement; identification; information; law; law enforcement; online; vehicles cache: fcis-11543.pdf plain text: fcis-11543.txt item: #53 of 872 id: fcis-11846 author: Lin, Hongjun title: Adversarial Training of SwinIR Model for Face Super-Resolution Processing date: 2023 words: 2918 flesch: 37 summary: With the rapid development of computer vision and artificial intelligence technologies, face image super-resolution processing plays a crucial role in improving the accuracy and performance of facial recognition and related applications. lin2669875691@gmail.com Abstract: This research aims to apply the SwinIR model to perform face image super-resolution processing using adversarial training techniques, thereby enhancing facial image features. keywords: image; model; resolution; super; swinir; training cache: fcis-11846.pdf plain text: fcis-11846.txt item: #54 of 872 id: fcis-11851 author: Yin, Di; Zhang, Chenya; Lu, Xindi title: Dynamic Analysis of Single Pile Wind Power Foundation Structure date: 2023 words: 2775 flesch: 56 summary: The results show that the simplified boundary condition method proposed in this paper is suitable for modal analysis of single pile offshore wind power foundation structure. An equivalent spring element method considering stiffness is proposed as a new boundary condition simplification method, and its analysis results are compared with those of two reference models to verify its applicability to single pile offshore wind power foundation structure. keywords: foundation; method; pile; structure; wind cache: fcis-11851.pdf plain text: fcis-11851.txt item: #55 of 872 id: fcis-11956 author: Zhang, Xinyue; Wang, Jin; Li, Lijun; Sun, Shouyi; Wang, Zaiqiang title: Load Analysis of Connectors for Floating Structures at Sea date: 2023 words: 3684 flesch: 53 summary: Therefore, when analyzing the load of floating structure connectors, the load caused by wind current must be considered. In AQWA software, the hinged connection between floating structure modules is simulated by releasing the constraint around the y-axis at the connection point and constraining other degrees of freedom. keywords: angle; connector; connector load; load; load amplitude; sea; structure; wave; wind cache: fcis-11956.pdf plain text: fcis-11956.txt item: #56 of 872 id: fcis-11957 author: Li, Guowei; Yang, Shanwei; Li, Sai; Jian, Jie; Li, Juan title: Application and Research based on ANOVA and Logistic Regression Models date: 2023 words: 1832 flesch: 47 summary: Binary logistic regression model is also one of the most classical methods of machine learning. Research on influencing factors of rural revitalization based on binary logistic regression model: From the perspective of grassroots cadre Contemporary Economy, 2022, 39 (07):106-110. keywords: anova; glass; oxide; regression; results cache: fcis-11957.pdf plain text: fcis-11957.txt item: #57 of 872 id: fcis-12004 author: Yu, Zefeng title: Research on Video Detection Method of Mudslide based on Inflated 3D Convolutional Neural Network date: 2023 words: 3522 flesch: 49 summary: Also, because the video captured by the camera has a certain degree of noise as well as light and shadow variations that can cause a certain amount of error in the results of the data, this paper uses the I3D training model to extract video features and the extracted features are used to calculate the anomaly score using the Sigmoid activation function, and based on the anomaly score, it is predicted whether or not an anomalous event occurs. 3.3. Next, the input is a video clip consisting of a series of consecutive video frames that are closely connected in time and represent video content over a period of time. keywords: detection; example; i3d; learning; model; mudslide; paper; training; video cache: fcis-12004.pdf plain text: fcis-12004.txt item: #58 of 872 id: fcis-12005 author: Zhang, Xusong; Rodavia, Maria Rosario title: Population Spatialization based on Random Forest Model and Multi-source Geospatial big data date: 2023 words: 2547 flesch: 46 summary: By performing a dimensionality reduction process on a large range of population data, we have obtained grid data with a more accurate and semantically rich description of population density in the smallest administrative region, this indicates that the progressive forest model has better population spatialization results compared to traditional linear regression models. The low spatiotemporal resolution of traditional population data makes it unsuitable for spatial analysis, which poses scientific difficulties in understanding the natural and social coupling mechanisms of sustainable development at multiple scales. keywords: analysis; data; distribution; forest; guizhou; level; model; population; spatialization cache: fcis-12005.pdf plain text: fcis-12005.txt item: #59 of 872 id: fcis-12008 author: Li, Yue; Gao, Guokang title: Large-scale Passenger Behavior Learning and Prediction in Airport Terminals based on Multi-Agent Reinforcement Learning date: 2023 words: 5404 flesch: 51 summary: Algorithm 1 Output: collection of agents 1 Load the airport terminal simulation environment, initialize the agent parameters 2 Set up and initialize a shared Q∗ table for each group and initialize the Q-value for each agent 3 Run the airport terminal simulation environment and obtain observations 4 Learning process of the agent for agent Independent learning of multi-agent may lead to environmental instability and long convergence time. keywords: action; agent; airport; data; learning; multi; number; passenger; reinforcement; terminal; time cache: fcis-12008.pdf plain text: fcis-12008.txt item: #60 of 872 id: fcis-12121 author: Li, Tongzhuang; Li, Hongyu title: Research on Production Prediction and Control of Mechanized Production Wells based on Neural Networks date: 2023 words: 3066 flesch: 57 summary: [8] We have developed a liquid production control technology for oil production wells based on layered oil recovery, which achieves layered liquid production control by adjusting the opening of production valves at all levels. Field experiments have shown that optimizing the liquid production rate of production wells based on this model can increase the recovery rate of well groups by 1.5%, which is of great significance for reservoir development; Literature keywords: control; data; network; neural; oil; production; wells cache: fcis-12121.pdf plain text: fcis-12121.txt item: #61 of 872 id: fcis-12144 author: Bai, Liang; Ding, Xuewen; Chang, Limei title: Remote Sensing Target Detection Algorithm based on CBAM-YOLOv5 date: 2023 words: 2391 flesch: 53 summary: Therefore, the convolutional attention CBAM structure is introduced into the C3 module to enhance the feature extraction capability and improve the problem of small target feature maps containing less information. With the rapid development of remote sensing satellite technology and image processing technology, the number of highly informative and high- resolution remote sensing image data is increasing day by day, making remote sensing target detection become a research hotspot in the field of remote sensing, and has been widely used in military security, rescue and search and other aspects. keywords: attention; detection; feature; figure; model; sensing; structure cache: fcis-12144.pdf plain text: fcis-12144.txt item: #62 of 872 id: fcis-12182 author: Yao, Xin title: Research on High Precision Temperature Acquisition System for Radiofrequency Ablation System date: 2023 words: 1396 flesch: 55 summary: Effects of control temperature, ablation time, and background tissue in radiofrequency ablation of osteoid osteoma: a computer modeling study. In this mode, the accuracy of temperature sampling is critical. keywords: ablation; radiofrequency; temperature; thermocouple; value cache: fcis-12182.pdf plain text: fcis-12182.txt item: #63 of 872 id: fcis-12266 author: Liu, Daiji title: Research on Object Trajectory Detection System Based on Computer Vision date: 2023 words: 2577 flesch: 46 summary: China Abstract: The main task of object trajectory detection is to collect and synthesize all kinds of information generated in the process of object motion, and get the displacement information of object in 3D space. In this paper, an object trajectory detection system based on computer vision is studied to realize object trajectory detection. keywords: acceleration; computer; detection; object; system; trajectory; vision cache: fcis-12266.pdf plain text: fcis-12266.txt item: #64 of 872 id: fcis-12278 author: Li, Shilong title: Research on the Application of Machine Learning in the Real Time Decision System of Autonomous Vehicles date: 2023 words: 2776 flesch: 44 summary: Among them, the accuracy of driving decision is directly related to road traffic safety. This article conducts research on the application of machine learning in real-time decision-making systems for autonomous vehicles. keywords: decision; driving; machine; making; system; time; vehicles cache: fcis-12278.pdf plain text: fcis-12278.txt item: #65 of 872 id: fcis-12285 author: Ling, Yun title: Research on the Application of Convolutional Neural Network Model in Night Surveillance Video Image Enhancement date: 2023 words: 2603 flesch: 50 summary: This algorithm can effectively improve the quality of low light images and exhibit superiority on multiple public datasets. This article proposes a low light image enhancement algorithm based on CNN model, which can properly enhance the quality of low light images and perform well on multiple common datasets. keywords: algorithm; color; enhancement; image; light; network; quality cache: fcis-12285.pdf plain text: fcis-12285.txt item: #66 of 872 id: fcis-12288 author: Lei, Yichen title: Application of Artificial Intelligence Technology in the Optimal Deployment of Wireless Sensor Network Nodes date: 2023 words: 2587 flesch: 39 summary: Given the target area range, the number and position of sensor nodes are determined through AI technology, which is the network layout for a given target area. Due to the limited energy of sensor nodes, minimizing energy consumption and maximizing network lifespan are the main goals of designing WSN. keywords: area; deployment; network; nodes; sensor; wsn cache: fcis-12288.pdf plain text: fcis-12288.txt item: #67 of 872 id: fcis-12312 author: Huang, Shihua title: Review on Information Privacy Protection based on Blockchain Principle date: 2023 words: 5213 flesch: 41 summary: Foreign countries tend to focus more on blockchain and its related technologies, while domestic countries demonstrate a greater interest in the application of blockchain privacy technology. These challenges are crucial to address when applying blockchain privacy technology. keywords: blockchain; computer; data; information; journals; literature; network; privacy; protection; research; security; technology; transaction cache: fcis-12312.pdf plain text: fcis-12312.txt item: #68 of 872 id: fcis-12348 author: Chen, Xiaojie title: Introduction and Analysis of Python Software date: 2023 words: 2115 flesch: 55 summary: This can work for us to deal with excel files or other files to bring more features can be used, but also become a better tool to utilize to work. Python's xlrd Module In Python, the xlrd library is a very commonly used library for reading excel files, and it can provide precise and fine- grained control over the reading of excel files. keywords: file; module; people; python; work cache: fcis-12348.pdf plain text: fcis-12348.txt item: #69 of 872 id: fcis-12441 author: Bu, Zhenhao; Wu, Chengshuo; Li, Huining title: Optimization Model of Heliostat Field Layout based on Genetic Algorithm date: 2023 words: 2986 flesch: 49 summary: In the production process of heliostat mirrors, there are certain tracking accuracy and face shape accuracy requirements. Scatter plot of solar altitude angle versus month keywords: angle; efficiency; field; heliostat; mirror; sun cache: fcis-12441.pdf plain text: fcis-12441.txt item: #70 of 872 id: fcis-12442 author: Jin, Yanrong; Gong, Lingxin title: Research on Knowledge Creation and Innovation Method based on Deep Learning and Human-machine Collaboration Model date: 2023 words: 2687 flesch: 32 summary: Knowledge creation and innovative development aim to provide content that meets expected standards for the knowledge economy and is committed to continuously improving knowledge quality and enhancing knowledge satisfaction. According to the framework, the human-machine collaboration model should ensure the effective realization of knowledge content, 50 establish professional standards for knowledge creation and innovation output, capture knowledge quality through technologies such as knowledge assessment systems, and measure knowledge satisfaction using knowledge cycle methods. keywords: collaboration; development; human; knowledge; learning; quality cache: fcis-12442.pdf plain text: fcis-12442.txt item: #71 of 872 id: fcis-12444 author: Zheng, Shi title: Research on the Bias Sampling RRT Algorithm for Supermarket Chain Distribution Routes under the O2O Model date: 2023 words: 2871 flesch: 49 summary: The Bias Sampling RRT algorithm, as a path search method for time window vehicle routing problems, can find the optimal path that meets time window constraints. The differences between them are manifested as follows: (1) Different research fields: RRT algorithm is mainly applied in fields such as robot navigation and autonomous driving, aiming to find the optimal path for robots or vehicles from the starting point to the target point. keywords: algorithm; routing; rrt; time; vehicle; window cache: fcis-12444.pdf plain text: fcis-12444.txt item: #72 of 872 id: fcis-12445 author: Liang, Chengxu; Dong, Jianshe title: A Survey of Deep Learning-based Facial Expression Recognition Research date: 2023 words: 3658 flesch: 50 summary: However, in the natural real environment and various interference (such as lighting, age and ethnicity), facial expression recognition will face many challenges. Facial expression recognition is to identify facial expressions to carry out emotion analysis, and emotion analysis can be analyzed with the help of facial expressions, speech, text, video and other signals. keywords: data; emotion; expression; expression recognition; fusion; information; learning; multimodal; recognition; research; sets cache: fcis-12445.pdf plain text: fcis-12445.txt item: #73 of 872 id: fcis-12446 author: Zhang, Hui; Yang, Xiaoping title: Aphid Detection Network from Global to Local date: 2023 words: 3786 flesch: 50 summary: In the only feature map faced by the detection head, pests are concentrated, and using only three anchor boxes may lead to a low recall rate for small target detection. However, applying target detection solutions to practical field pest recognition requires considering more factors such as lighting and occlusion. keywords: detection; feature; figure; head; images; information; network; pest; targets cache: fcis-12446.pdf plain text: fcis-12446.txt item: #74 of 872 id: fcis-12471 author: Li, Hanrong; Hong, Xizhi; Hu, Baoyan title: Analysis of Arrhythmia Features based on LightGBM and Kmeans Feature Extraction date: 2023 words: 3052 flesch: 55 summary: Further Subdivision of Hazard Category 4 by Elbow Method Based on the above analysis and further observation of the cluster center, it can be concluded that risk category 1 can be further divided into two categories, namely low-frequency ventricular tachycardia (VTLR), ventricular premature beats (B), high ventricular ectopic beats (HGEA), and ventricular escape rhythm (VER) Based on the above summary, this article draws images to observe the numerical variance of each area with a danger level of 4, and the results are as follows Figure 7. S-T band: The shape and position of the S-T band may vary in low-frequency ventricular tachycardia (VTLR), ventricular premature beats (B), high ventricular ectopic beats (HGEA), and ventricular escape rhythm (VER). keywords: analysis; band; beats; classification; wave cache: fcis-12471.pdf plain text: fcis-12471.txt item: #75 of 872 id: fcis-12803 author: Meng, Fanrun; Liu, Chen; Zhu, Zhiren; Zhou, Liming title: UAV Target Detection Algorithm with Improved YOLOv7 date: 2023 words: 2387 flesch: 50 summary: In this study, we propose an improved algorithm based on YOLOv7 to enhance the performance and robustness of UAV target detection. 5. Conclusion Aiming at the challenges faced by UAV target detection with YOLOv7 algorithm's everything is fine except for one small defect, this study proposes an improved algorithm for UAV target detection based on YOLOv7, which improves the 75 accuracy of UAV target detection by introducing BiFPN and GAM attention mechanism. keywords: algorithm; detection; features; model; target; uav; yolov7 cache: fcis-12803.pdf plain text: fcis-12803.txt item: #76 of 872 id: fcis-12817 author: Li, Mengpei; Pan, Jun title: Chinese E-commerce NER Using RoBERTa-wmm under the Machine Reading Comprehension Paradigm date: 2023 words: 3922 flesch: 59 summary: tail tailL L P Y (11)  : : :,head tail head tail head tailL L P Y (12) Where headY , tailY , :head tailY represent the real labels about entity head, tail and entity matching span respectively. To get the probability of predicted entity head and tail matching, we use binary classification as follows:   keywords: commerce; dataset; entity; head; information; model; mrc; question; recognition; tail cache: fcis-12817.pdf plain text: fcis-12817.txt item: #77 of 872 id: fcis-12818 author: Dong, Xiuhuan; Li, Shixin; Zhou, Liming title: Research on Improved Method based on YOLOV5s Target Detection Model date: 2023 words: 2384 flesch: 51 summary: The average accuracy (mAP) of the YOLOv7 object detection network model can reach 80.3%, which is 1.5% lower than that of the improved model. The SE attention mechanism helps the network to better focus on important feature channels, thereby improving model performance. keywords: accuracy; box; detection; model; network; object; yolov5s cache: fcis-12818.pdf plain text: fcis-12818.txt item: #78 of 872 id: fcis-1292 author: Bai, Mingxiao title: Numerical simulation of charge blasting without coupling to air media date: 2022 words: 2028 flesch: 54 summary: Frontiers in Computing and Intelligent Systems ISSN: 2832-6024 | Vol. 1, No. 1, 2022 26 Numerical simulation of charge blasting without coupling to air media Mingxiao Bai 1, * 1 School of Civil Engineering, Henan Polytechnic University, Jiaozuo 454000, China; * Corresponding author: Mingxiao Bai (Email: 1409950099@qq.com). Air material model and equation of state parameters ρ0 Kg·m-3 C0 C1 C2 C3 C4 C5 C6 E KJ·m-3 V 1.293 0 0 0 0 0 0 0 235 1 2.2.3. keywords: blasting; coefficient; figure; hole; model; wall cache: fcis-1292.pdf plain text: fcis-1292.txt item: #79 of 872 id: fcis-1293 author: Yang, Jie title: Research progress on the influence of geopolymer grouting material properties date: 2022 words: 3208 flesch: 42 summary: Silicon aluminate raw material Aluminosilicate raw material is the reactive base material 31 of geopolymer grouting material, its activity degree and the content of calcium oxide have an important influence on the working performance of geopolymer grouting material. In this paper, the ratio and compressive strength results of composite silica- aluminate materials of geopolymer grouting materials in the study are summarized as shown in Table 1. keywords: cement; compressive; geopolymer; grouting; materials; properties; sodium; strength; temperature cache: fcis-1293.pdf plain text: fcis-1293.txt item: #80 of 872 id: fcis-12974 author: Cai, Kunpeng; Rodavia, Maria Rosario title: XGBoost Analysis based on Consumer Behavior date: 2023 words: 3573 flesch: 50 summary: By digging deeper into consumer behavior data, businesses can better meet customer needs, improve sales efficiency, and achieve sustainable competitive advantage, and this research provides strong support for the use of machine learning techniques to optimize market strategies. Finally, we summarize the main findings of this study, highlighting the potential applications of XGBoost analytics based on consumer behavior in marketing and business decisions. keywords: behavior; consumer; customer; data; figure; model; prediction; xgboost cache: fcis-12974.pdf plain text: fcis-12974.txt item: #81 of 872 id: fcis-12979 author: Li, Yinian; Tan, Gongquan title: Attitude Control of Quadrotor UAV Using Improved Active Disturbance Rejection Control date: 2023 words: 3750 flesch: 56 summary: Through MATLAB/Simulink simulation, the fastness, overshoot and anti-jamming performance of the improved ADRC in quadrotor UAV attitude control are better than that of the traditional ADRC. Quadrotor UAV control system 3.4 Attitude Control Based on Active Disturbance Rejection Control keywords: adrc; control; function; quadrotor; system; uav cache: fcis-12979.pdf plain text: fcis-12979.txt item: #82 of 872 id: fcis-12986 author: Nie, Linping title: Practical Application of Informatization Teaching Tool "Super Star Learning " in the Teaching Process of Software Engineering Major Courses date: 2023 words: 1888 flesch: 33 summary: Keywords: Informatization; Super Star Learning; Teaching Resources; Course Teaching. 4. Take Front-end Development Technology Course as an Example, Use Super Star Learning to Implement Course Teaching. keywords: course; learning; star; super; teaching cache: fcis-12986.pdf plain text: fcis-12986.txt item: #83 of 872 id: fcis-13109 author: Wang, Shuhan title: Survey of Malicious PDF Attacks date: 2023 words: 2272 flesch: 35 summary: The model encompasses components like intrusion target detection, malicious attack code detection, attack code distribution, Trojan program or link control, and extraction of anomalous attack traffic data. Subsequently, malicious attack codes and their distribution are detected for the targeted network nodes. keywords: attack; code; detection; document; javascript; network; pdf cache: fcis-13109.pdf plain text: fcis-13109.txt item: #84 of 872 id: fcis-13113 author: Wang, Wenbo title: A Review of Machine Translation Quality Assessment Methods date: 2023 words: 2313 flesch: 43 summary: xiaobo.0412@outlook.com Abstract: Machine translation quality assessment plays a crucial role in enhancing the performance of machine translation systems. On the other hand, automatic evaluation methods are cost-effective and rapid, but their evaluation results do not match the expertise of human evaluators. keywords: assessment; evaluation; methods; quality; translation cache: fcis-13113.pdf plain text: fcis-13113.txt item: #85 of 872 id: fcis-13124 author: Li, Qixuan title: Joint Modelling of Slot Filling and Intent Detection in Constrained Resource Scenarios date: 2023 words: 3571 flesch: 51 summary: For the study of joint models for NLU, the earliest work used a three-layer CRF, where the three layers are token features, slot labels, and intent labels, whereas this architecture is better than performing two sub-tasks in a pipeline, and the first neural model for solving the joint task is (different from recurrent neural networks) Conclusion This study aims to explore the construction of joint models for intent recognition and slot filling in a constrained resource environment. keywords: dataset; filling; graph; intent; language; model; node; resource; slot cache: fcis-13124.pdf plain text: fcis-13124.txt item: #86 of 872 id: fcis-13128 author: Zhang, Juanhua title: Research on Derived Tasks and Realistic Applications of Segment Anything Model: A Literature Review date: 2023 words: 3039 flesch: 43 summary: The author will explore the applications, advantages, and challenges of SAM model in image segmentation, object detection, image restoration, remote sensing, and medical fields, aiming to provide inspiration for researchers in the field of computer vision. The application of SAM model in multiple fields has demonstrated its potential and value in image segmentation, object detection, image restoration, as well as remote sensing and medical fields. keywords: detection; image; model; sam; segmentation; tasks cache: fcis-13128.pdf plain text: fcis-13128.txt item: #87 of 872 id: fcis-13134 author: Guo, Quanyi title: Occluded Face Recognition based on Deep Learning date: 2023 words: 3383 flesch: 53 summary: Compared to the traditional sparse representation and the dictionary processing method of occlusion, deep learning- based face recognition methods are being used more and more widely in the field of face recognition. However, the accuracy of face recognition in traditional algorithm is influenced by objective factors such as shooting Angle, the illumination intensity, mask shielding, eye shielding, which makes the recognition accuracy in the presence of face mask. keywords: data; face; face recognition; network; offset; recognition; vector cache: fcis-13134.pdf plain text: fcis-13134.txt item: #88 of 872 id: fcis-13139 author: Jia, Shan title: 3D Human Pose Estimation: A Survey date: 2023 words: 3163 flesch: 47 summary: The challenge in 3D HPE lies in recovering 3D human pose from 2D images, as there is more uncertainty in the estimation process, and it requires greater computational and spatial 125 resources compared to 2D images. [2, 3] 2D to 3D Lifting: This method infers 3D human pose based on 2D HPE (2D HPE) and maps 2D pose to 3D pose. keywords: hpe; human; methods; person; pose cache: fcis-13139.pdf plain text: fcis-13139.txt item: #89 of 872 id: fcis-13141 author: Zhang, Yuming title: Design of Internet of Vehicles Routing Protocol based on Prior Probability date: 2023 words: 2052 flesch: 45 summary: Vehicle ad-hoc networks V2X communication protocol based on channel propagation model. In The Research on Vehicle Network Routing Algorithm Based on Q Learning, Liu Chao used Q learning algorithm to improve the problem of discarding data packets due to the limited storage space of vehicle nodes in VANET keywords: information; message; probability; protocol; routing; vehicles cache: fcis-13141.pdf plain text: fcis-13141.txt item: #90 of 872 id: fcis-13142 author: Wu, Zhouli title: Research on Image Super-Resolution Using Attention Mechanisms based on Super-Resolution Generative Adversarial Network date: 2023 words: 2767 flesch: 40 summary: [3], which not only improved image quality but also inspired subsequent research. In this experiment, a multi-level residual network was constructed by applying normalization through three layers of convolution and GN layers, thereby improving image quality. keywords: image; loss; model; resolution; srgan; super; training cache: fcis-13142.pdf plain text: fcis-13142.txt item: #91 of 872 id: fcis-13144 author: Yi, Xiaowen title: Accurate Obstacle Avoidance for Quadcopter UAVs under Moving Obstacle Conditions based on A* Algorithm date: 2023 words: 2994 flesch: 61 summary: The shortest route for UAV obstacle avoidance under the conventional A* algorithm As shown in the figure 9 and figure 10 is the obstacle avoidance route of the improved A* algorithm in the same map, according to different animals in different environments have different alert ranges, we set n=1, n=2 respectively. Analysis of Results The shortest route for UAV obstacle avoidance under the conventional A* algorithm is shown in Figure 8. keywords: algorithm; animals; figure; obstacle; path; point; uav cache: fcis-13144.pdf plain text: fcis-13144.txt item: #92 of 872 id: fcis-13146 author: Zhang, Zili title: Based on YOLO v3 Target Recognition Algorithm as Vehicle Tracking Algorithm Analysis date: 2023 words: 3431 flesch: 54 summary: In the process of vehicle target recognition, a suitable target recognition algorithm for the vehicle in the traffic video of the research object of this paper is given by comparing various target recognition algorithms, and related analysis is carried out. In the process of vehicle target tracking, by comparing various target tracking algorithms, the appropriate target tracking algorithm for the vehicle in the traffic video of the research object of this paper is given, and the relevant analysis is carried out. keywords: data; recognition; set; target; tracking; traffic; training; vehicle cache: fcis-13146.pdf plain text: fcis-13146.txt item: #93 of 872 id: fcis-13147 author: Xu, Yuanfang title: Research on Weibo New Word Recognition based on Weibo Data and Statistical Information date: 2023 words: 2407 flesch: 50 summary: Considering that topic names are generally not too long, the maximum value of N is 6, which means extracting consecutive strings of length not exceeding from topic names as candidate Weibo new word strings. China Abstract: One of the key challenges in the field of Chinese information processing is the recognition of Weibo new words, which has a profound impact on machine translation and text classification. keywords: filtering; information; recognition; string; weibo; word cache: fcis-13147.pdf plain text: fcis-13147.txt item: #94 of 872 id: fcis-13148 author: Li, Weifu; Cai, Yichong; Huang, Jinyu title: Sichuan Cuisine Recognition Method based on Residual Neural Network date: 2023 words: 3531 flesch: 43 summary: [12] addressed the issue of accuracy errors caused by the large inter-class similarity in Sichuan cuisine dish images using the maximum inter-class loss function. To validate the model's performance, this study conducted comparative experiments, comparing the proposed method with lightweight network models such as EfficientNet keywords: attention; convolution; cuisine; feature; image; model; network; recognition; rgbnet; sichuan cache: fcis-13148.pdf plain text: fcis-13148.txt item: #95 of 872 id: fcis-13149 author: Wang, Jianyan; Zhou, Yapeng; Bai, Qinghua; Zhao, Yonggang title: Ultrasonic Scanning for Lithium-ion Battery Inspection date: 2023 words: 2042 flesch: 38 summary: In addition, ultrasonic scanning also emits high-frequency sound waves, and the ultrasonic data acquisition card can be used to collect and analyze the ultrasonic beams passing through the interior of lithium batteries, and according to the ultrasonic characteristics of the received ultrasonic waves can be used to assess the internal structure of the lithium batteries and the characteristics of the defects, and at the same time, it can also be used to assess the performance and safety performance of the batteries. The effects of open-circuit voltage on battery performance during electrolyte filling were clearly demonstrated by precise experimental data and detailed analysis results. keywords: batteries; battery; detection; ion; lithium; scanning; ultrasonic cache: fcis-13149.pdf plain text: fcis-13149.txt item: #96 of 872 id: fcis-1369 author: Liang, Shiping; Jiang, Ling; Zhang, Dianjuan title: Analysis on the Impact of Digital Economy Development on Carbon Emissions in Anhui Province date: 2022 words: 4742 flesch: 31 summary: Xie Yunfei (2022) analyzed the impact of blockchain on industrial green development, Xu Zhao et al (2021) analyzed the impact of digital Finance on pollution emissions, but such research cannot fully prove the substantial impact of digital economy on carbon emissions, and the theory of the effect of digital economy development on carbon emissions still needs to be improved. This study introduces the variable of digital economy development into the theoretical research framework of influencing factors of carbon emission reduction in Anhui Province, and systematically examines the role of digital economy in urban carbon emission reduction in Anhui Province. keywords: anhui; carbon; carbon emissions; development; digital; economy; emissions; energy; green; innovation cache: fcis-1369.pdf plain text: fcis-1369.txt item: #97 of 872 id: fcis-1370 author: Ma, Qianrong; Yang, Le; Zhou, Zejiong title: The Present Situation, Problems and Countermeasures of Manufacturing Investment in Anhui Province date: 2022 words: 4813 flesch: 38 summary: The trend relationship between Anhui manufacturing investment and national manufacturing investment shows that, on the one hand, although the efficiency level of China's manufacturing industry has been steadily improved, the downstream industries, especially small and micro enterprises, are still under great pressure in the process of capacity reduction, the vitality of market players needs to be stimulated, and the manufacturing industry needs to operate steadily to improve quality and efficiency; On the other hand, it shows that the strategy of building a strong manufacturing province in Anhui has formed a joint force to promote the high-quality development of the manufacturing industry, and provides a solid guarantee for the development of manufacturing investment. At present, although the strategy of building a strong manufacturing province in Anhui Province has achieved certain results, there are still some problems in Anhui manufacturing investment, which require us to attach great importance to. keywords: anhui; growth; industry; investment; manufacturing; manufacturing industry; manufacturing investment; rate cache: fcis-1370.pdf plain text: fcis-1370.txt item: #98 of 872 id: fcis-13801 author: Yu, Xinqiang title: Optimization of Artificial Intelligence Algorithm based on Neural Network in Complex System date: 2023 words: 2900 flesch: 44 summary: NN model is also widely used in complex system optimization. Introduction In the 1940s, American psychologist McCulloch and mathematician Pitts put forward the M-PNN model, which started the theoretical research of NN model keywords: algorithm; model; optimization; power; system cache: fcis-13801.pdf plain text: fcis-13801.txt item: #99 of 872 id: fcis-13810 author: Liu, Zicheng title: Application of Efficient Algorithm in Dynamic Simulation of Viscoelastic Fluid in 3D Animation date: 2023 words: 2384 flesch: 36 summary: Therefore, this paper will put forward some improvement measures to solve these problems, so that the efficient algorithm is more suitable for the application of viscoelastic fluid dynamic simulation in 3D animation. Therefore, this paper will put forward some improvement measures to solve these problems, so that the efficient algorithm is more suitable for the application of viscoelastic fluid dynamic simulation in 3D animation. keywords: animation; fluid; simulation; viscoelastic cache: fcis-13810.pdf plain text: fcis-13810.txt item: #100 of 872 id: fcis-13814 author: Feng, Ying; Wang, Yongqin title: Intelligent Diagnostic System Development based on Artificial Intelligence Technology date: 2023 words: 4658 flesch: 36 summary: 7. Conclusion With the scarcity of medical resources, the demand for intelligent medical systems is becoming increasingly urgent. In this article, a medical dialogue robot architecture based on medical dialogue diagnosis technology, medical knowledge graph technology, and inference machine technology is proposed to build an intelligent diagnosis architecture. keywords: algorithm; data; diagnosis; dialogue; disease; intelligence; knowledge; symptom; system; technology cache: fcis-13814.pdf plain text: fcis-13814.txt item: #101 of 872 id: fcis-13836 author: Shen, Zepeng title: Algorithm Optimization and Performance Improvement of Data Visualization Analysis Platform based on Artificial Intelligence date: 2023 words: 3157 flesch: 26 summary: Data visualization analysis can transform complex data into intuitive graphics, charts, or visual interfaces, helping users better understand and analyze data, discover hidden patterns and trends in the data, and make corresponding decisions. The rapid development of artificial intelligence technology has brought new opportunities and challenges to data visualization analysis. keywords: algorithms; analysis; data; intelligence; technology; visualization cache: fcis-13836.pdf plain text: fcis-13836.txt item: #102 of 872 id: fcis-13837 author: Ming, Daoyang; Xiong, Weicheng title: The Source Code Comment Generation based on Abstract Syntax Tree date: 2023 words: 7141 flesch: 60 summary: Technically, we also have a third dataset containing the default SBT representation (with code words) and the pre- processed comment, which we use for experiments to compare our approach to the baselines. Due to the special grammar and syntax structure of programming languages and various shortcomings of different deep neural networks, the accuracy of existing code summarization approaches is not good enough. keywords: approach; ast; attendgru; bleu; code; comment; conference; input; java; methods; model; sbt; sequence; source; text cache: fcis-13837.pdf plain text: fcis-13837.txt item: #103 of 872 id: fcis-13838 author: Wang, Qin title: The Path Selection of China's Chip Independent Innovation and the Influence of United States Technology Blockade date: 2023 words: 2748 flesch: 41 summary: These measures are helpful to improve the independent innovation ability of China chip industry and accelerate the development of China chip industry. Classification of technological innovation modes (2) Industrial chain upgrade: China chip industry needs to speed up the industrial chain upgrade and improve the level and quality of chip design, manufacturing, packaging and testing. keywords: china; chip; independent; industry; innovation cache: fcis-13838.pdf plain text: fcis-13838.txt item: #104 of 872 id: fcis-13841 author: Zhang, Minghui title: A Zero-Cost Darts Base on Multi-Step Optimization date: 2023 words: 2605 flesch: 61 summary: Knas: Green neural architecture search. Zen-NAS[14] uses the LGA metric to evaluate the performance of candidate architectures in NAS, which is a derived metric of NTK and uses both label information and NTK metric. keywords: architecture; cost; darts; learning; optimization; search; step; time cache: fcis-13841.pdf plain text: fcis-13841.txt item: #105 of 872 id: fcis-13847 author: Jiang, Qirui; Liu, Yuqi title: Object Detection for Aircraft Turnover Milestone based on Modified date: 2023 words: 5644 flesch: 56 summary: Add a small target detection head to improve the ability of small target detection; The up-sampling module OVRAFE is introduced to reduce the information loss in the up-sampling process. The improved model makes up for the performance shortcomings of small target detection in foggy days, and the average detection accuracy on the real foggy day test set is 76.2%, which is 3.32% higher than that of the original model, basically meeting the task requirements. keywords: algorithm; detection; feature; frame; function; head; information; loss; map; model; module; network; set; target; target detection; yolo cache: fcis-13847.pdf plain text: fcis-13847.txt item: #106 of 872 id: fcis-13848 author: Huang, Songling; Wen, Zhenji; Li, Hanling title: Research on Arrhythmia Classification and Risk Degree Prediction based on Deep Neural Network and Convolutional Neural Network date: 2023 words: 1866 flesch: 52 summary: China Abstract: In this study, a method of arrhythmia classification and risk prediction based on deep neural network and convolutional neural network (CNN) is proposed for ECG data. Our goal is to learn a function that maps the input ECG data to the output label Y, as shown in Figure 2. keywords: arrhythmia; data; ecg; model; network cache: fcis-13848.pdf plain text: fcis-13848.txt item: #107 of 872 id: fcis-13852 author: Liu, Chen; Meng, Fanrun; Zhu, Zhiren; Zhou, Liming title: Object Detection of UAV Aerial Image based on YOLOv8 date: 2023 words: 3054 flesch: 52 summary: Comparison of model detection performance before and after improvement 5. Currently, target detection algorithms based on deep learning are mainly divided into two-stage model represented by Faster-RCNN keywords: accuracy; box; detection; loss; model; module; object; structure; target; training; yolov8 cache: fcis-13852.pdf plain text: fcis-13852.txt item: #108 of 872 id: fcis-13854 author: Wang, Yufan; Leng, Yuqing; Chen, Yuhong title: Analysis of Hot Air Invasion Characteristics of Cold Storage Smart Door During Opening and Closing Process date: 2023 words: 2847 flesch: 47 summary: In this paper, we introduce the characteristics of hot air intrusion in cold storage doors from several aspects, first of all, the role and application of cold storage are generally introduced, and then the adverse effects of hot air intrusion into cold storage, the environmental impact brought by the form of cold storage doors, the impact of cold storage door opening time on cold storage, and suggestions for hot air intrusion into cold storage. Analyze the hazards and countermeasures of air intrusion from cold storage doors [J]. keywords: air; cold; storage; storage door; temperature; warehouse cache: fcis-13854.pdf plain text: fcis-13854.txt item: #109 of 872 id: fcis-13855 author: Meng, Fanrun; Zhu, Zhiren; Zhou, Liming title: Non-contact Infrared Temperature Measuring Device based on stm32 date: 2023 words: 2728 flesch: 58 summary: Infrared temperature measurement module does not measure temperature. This topic through the STM32F103C8T6 microcontroller control system operation, the use of ultrasonic ranging module for real-time monitoring of the distance of the person under test, when the person under test into the test range, the use of MLX90614 infrared temperature sensor for the test of the person under test for the test of the temperature of the person under test, once exceeded the set alarm value the system will beeping alert. keywords: data; display; microcontroller; module; sensor; system; temperature cache: fcis-13855.pdf plain text: fcis-13855.txt item: #110 of 872 id: fcis-13856 author: Feng, Ying; Luo, Chunyan title: Research on the Application of Big Data Analysis Platform in the Enterprise Management Optimization date: 2023 words: 5030 flesch: 32 summary: Data analysis platforms have become necessary analysis systems for various industries to explore and analyze data, assist daily business operations, and develop new business markets. Due to the DASE framework's design principles based on service- oriented and workflow architecture, enterprises is able to freely utilize IT components (databases, middleware, and machine learning models) from existing infrastructure and expose them as services used by data analysis platforms. keywords: analysis; analysis platform; business; data; data analysis; development; enterprise; knowledge; management; model; modeling; platform; requirements cache: fcis-13856.pdf plain text: fcis-13856.txt item: #111 of 872 id: fcis-13857 author: Zhu, Zhiren title: The Electronic Lock of Fingerprint Identification date: 2023 words: 2711 flesch: 47 summary: According to the existing level of development of fingerprint electronic locks, there are often the following two options: Program 1: fingerprint identification electronic lock based on STC89C51 microcontroller According to the design requirements of fingerprint identification and the internal structure and characteristics of STM32 series microcontroller, the overall design idea of the hardware of fingerprint identification electronic lock is proposed. keywords: design; fingerprint; fingerprint identification; lock; microcontroller; module; system cache: fcis-13857.pdf plain text: fcis-13857.txt item: #112 of 872 id: fcis-13858 author: Jiang, Han; Xian, Hequn title: A Sensitivity-based Location Privacy Protection Scheme in Vehicular Networks date: 2023 words: 5605 flesch: 62 summary: The scheme updates vehicle pseudonyms when the speed drastically drops or accelerates, while maintaining the same pseudonym for nearly constant speeds. Abstract: In recent times, the issue of vehicle location privacy has received increasing attention. keywords: access; group; information; location; privacy; pseudonym; scheme; sensitivity; time; user; vehicle cache: fcis-13858.pdf plain text: fcis-13858.txt item: #113 of 872 id: fcis-13859 author: Yang, Wendong title: The Advantages of Artificial Intelligence Application in Computer Technology date: 2023 words: 1982 flesch: 24 summary: This paper commences by expounding on the contemporary concept and characteristics of artificial intelligence technology, followed by a synthesis of the advantages of its implementation in the realm of computer network technology based on relevant literature. Notably, in the field of computer network technology, its utilization has significantly elevated the technological prowess of computer science, propelling computer systems towards a gradual trajectory of stability and intelligence. keywords: computer; data; information; intelligence; management; network; technology cache: fcis-13859.pdf plain text: fcis-13859.txt item: #114 of 872 id: fcis-13860 author: Lin, Shenrui; Li, Yuangang; Wang, Yaru title: Optimization Model of Survey Line Layout for Multibeam Bathymetric Systems date: 2023 words: 3138 flesch: 55 summary: Design a set of survey lines with the shortest measuring length that can completely cover the entire sea area to be surveyed, i.e., it is necessary to determine the direction of the survey lines and the spacing of adjacent survey lines. Schematic diagram of the distribution of survey lines The total length of the survey lines is 75,422.292km, and the overlap rate is 10.6%, which is in line with the condition that the overlap rate is between 10% and 20%, and it is also found that the survey lines are more dense in the shallow water area, and the arrangement of the survey lines is more sparse in the deep water area. keywords: direction; lines; model; multibeam; overlap; slope; survey line cache: fcis-13860.pdf plain text: fcis-13860.txt item: #115 of 872 id: fcis-13861 author: Chen, Tao; Luo, Zikun; Liu, Jinhui title: Research on Vegetable Commodity Pricing and Replenishment based on Planning Models and Genetic Algorithm date: 2023 words: 3192 flesch: 50 summary: The division of sales data into multiple intervals aims to analyze and reveal the general trend in sales volume to better understand the changes and distribution characteristics of sales data. There is a correlation between sales volume and time of year, especially during the period from April to October when the variety of vegetables is more abundant. keywords: analysis; category; correlation; data; paper; pricing; sales; sales volume; volume cache: fcis-13861.pdf plain text: fcis-13861.txt item: #116 of 872 id: fcis-13862 author: Zhou, Liming title: The Design of the Automatic Control Intelligent Ashbin date: 2023 words: 2122 flesch: 59 summary: Overall System Design Goals Automatic control of intelligent garbage bin design introduces a microcontroller for logic judgment to achieve intelligent operation, in order to achieve non-manual touch the lid of the garbage can, automatic control of intelligent garbage can design implementation will need to have a human body sensor recognition and automatic open and close the lid function, the design of the use of photoelectric sensors for human body recognition, when the sensor detects the human body to automatically open the lid of the garbage bin to reduce the transmission of viruses, and to facilitate garbage bins. It can better achieve the function of automatic control of intelligent garbage bins. keywords: bin; design; garbage; garbage bin; lid; module cache: fcis-13862.pdf plain text: fcis-13862.txt item: #117 of 872 id: fcis-13865 author: Xu, Hao; Xian, Hequn title: SCD: A Detection System for DDoS Attacks based on SAE-CNN Networks date: 2023 words: 5161 flesch: 49 summary: In complex real-world network environments, differentiating DDoS attack traffic from normal traffic is a challenging task, making it significant to effectively distinguish between attack types in order to resist DDoS attacks. In this paper, we propose a lightweight framework based on deep learning called SAE-CNN-Detection (SCD), which combines stacked autoencoder network (SAE) and convolutional neural network (CNN) for DDoS attacks detection. keywords: accuracy; attacks; classification; cnn; data; dataset; ddos; ddos attacks; detection; feature; layer; learning; model; network; scd; traffic cache: fcis-13865.pdf plain text: fcis-13865.txt item: #118 of 872 id: fcis-13998 author: Liang, Yu; Yu, Yadong; Wang, Yina; Li, Dunjun; Zhou, Zejiong title: Counterfeiting in Depth Synthesis based on Digital Watermarking date: 2023 words: 5701 flesch: 37 summary: For example, models such as a convolutional neural network (CNN) or a generative adversarial network (GAN) can be used for image forgery detection. Abstract: The purpose of this paper is to discuss and apply digital watermarking technology to solve the forgery problem in depth synthesis. keywords: algorithm; data; detection; embedding; extraction; forgery; image; information; media; technology; watermarking cache: fcis-13998.pdf plain text: fcis-13998.txt item: #119 of 872 id: fcis-13999 author: Yu, Xiaochuan; Ozdemir, Mary B.; Joshie, M. K. title: An Overview of Hyperspectral Image Classification by Data-driven Deep Learning date: 2023 words: 3197 flesch: 36 summary: These features can be obtained through three approaches: 1) mapping low- level spectral-spatial features to high-level ones using deep networks; 2) directly extracting deep features from original data or principal components; 3) fusing separate deep spectral and spatial features. In this section, we use the Salinas dataset to visualize deep features. keywords: classification; data; features; hsi; image; learning; networks; sensing cache: fcis-13999.pdf plain text: fcis-13999.txt item: #120 of 872 id: fcis-14008 author: Wang, Qiangchun title: On Development of Metaverse and Digital Ecology Safety date: 2023 words: 6152 flesch: 49 summary: The metaverse means that more and more of our lives, labor, leisure, time, wealth, happiness, and relationships will be spent in virtual worlds. Virtual worlds will have three fundamental properties: social presence, network continuity, multi-person sharing, and interoperability. keywords: data; development; digital; future; human; intelligence; internet; life; metaverse; people; reality; security; social; technology; users; world cache: fcis-14008.pdf plain text: fcis-14008.txt item: #121 of 872 id: fcis-14015 author: Zhang, Fufu; Chen, Tianxing title: Research on the Aided Design System of Linear Conveyor Equipment based on Haochen CAD date: 2023 words: 2781 flesch: 47 summary: This will greatly improve the design efficiency of designers while reducing the error rate in non-standard designs. Customization requirements: Linear conveyors are usually designed and manufactured according to the specific needs of users, so non-standard part design work needs to be customized according to the special requirements of each project. keywords: cad; design; development; length; linear; parts; standard; system cache: fcis-14015.pdf plain text: fcis-14015.txt item: #122 of 872 id: fcis-14020 author: He, Chunlin; Wu, Jiaye; Yang, Yujie title: Research on Expressway Pavement Crack Detection based on Improved YOLOv5s date: 2023 words: 4329 flesch: 51 summary: Firstly, a CBAM attention module was added to the backbone network of the improved YOLOv5 model to obtain more detailed features; Then, in the feature fusion layer, BiFPN weighted bidirectional feature pyramid network is used for multi-scale feature fusion, replacing the traditional feature pyramid (FPN)+pixel aggregation network (PAN) structure to enhance feature fusion. In common application examples, attention modules are often combined with feature fusion operations, but further experiments are needed to determine which position or positions in the network can achieve better results. keywords: cbam; crack; detection; feature; figure; fusion; input; model; module; network; road; structure cache: fcis-14020.pdf plain text: fcis-14020.txt item: #123 of 872 id: fcis-14021 author: Jin, Sheng title: Real Time Detection Algorithm for Escape Ladders based on YOLOv5s date: 2023 words: 3144 flesch: 54 summary: Optimize the network structure of YOLOv5s algorithm, strengthen shallow feature weights to enhance small target detection effectiveness, add attention mechanisms to increase the weight of small targets and their surrounding features, and use Mosaic methods for data augmentation to improve detection accuracy and recall. Performance Test Results of YOLOv5s Detection Algorithm on Self built Datasets Improved algorithm structure, added small object detection layer CA, improved anchor box, selected anchors that are more suitable for small objects, improved YOLOv5s algorithm, added small object detection layer, easy to analyze charts, optimized and adapted YOLOv5s algorithm, improved accuracy by 1.4% and recall by 1.2% mAP@0.5 keywords: algorithm; attention; detection; escape; model; network; object; yolov5s cache: fcis-14021.pdf plain text: fcis-14021.txt item: #124 of 872 id: fcis-14034 author: Li, Jiahao; Zuo, Qiongle; Bai, Zening; Wang, Wenliang; Zhang, Xinrui; Ding, Nan title: Research on LAN Networking Solution for Small and Medium-sized Enterprises Using Huawei Communication Equipment date: 2023 words: 2920 flesch: 27 summary: Using Huawei network devices to form a small business LAN[J]. Based on different network topologies, LANs can be categorized into the following types: (a) Bus-based LANs: All computers and network devices are connected to a common bus, through which data transmission takes place. keywords: communication; enterprises; equipment; huawei; lan; network; networking cache: fcis-14034.pdf plain text: fcis-14034.txt item: #125 of 872 id: fcis-14037 author: Cai, Mengying title: Study on Water Purification of Freshwater Aquaculture Pond based on Correlation Analysis date: 2023 words: 2470 flesch: 48 summary: In order to study the relationship between the main physical and chemical factors (total phosphorus, phosphate phosphorus, total nitrogen, nitrate nitrogen, nitrous nitrogen and ammonium nitrogen) in freshwater aquaculture ponds, we chose to monitor the contents of six physical and chemical factors in pond water, interstitial water and sediment for 15 weeks, and set up two monitoring points in each pond to avoid accidental data. In this paper, the relationship between six physical and chemical factors, including total phosphorus, phosphate phosphorus, total nitrogen, nitrate nitrogen, nitrous nitrogen and ammonium nitrogen, in pond water, interstitial water and sediment was mainly studied. keywords: chemical; factors; nitrogen; phosphorus; pond; water cache: fcis-14037.pdf plain text: fcis-14037.txt item: #126 of 872 id: fcis-14038 author: Liang, Zhanhao; Isakunovich, Batyrkanov Jenish title: Volleyball Action Recognition based on Skeleton Data date: 2023 words: 2346 flesch: 45 summary: Abstract: This research explores the intricacies of volleyball action recognition using skeleton data through the lens of the Long Short-Term Memory (LSTM) model. In this research, we embark on a journey through the world of volleyball action recognition, armed with the power and precision of skeleton data. keywords: action; data; lstm; model; recognition; skeleton; volleyball cache: fcis-14038.pdf plain text: fcis-14038.txt item: #127 of 872 id: fcis-14040 author: Hu, Yuxuan title: FPGA Hardware Acceleration Research and Implementation of Deep Learning Algorithms date: 2023 words: 2757 flesch: 51 summary: Therefore, it is a better trade-off choice to choose the appropriate number of fixed points for optimization, and sacrifice a small model accuracy to greatly improve the calculation and storage efficiency. [7] Wai, Y.J., Yussof, Z.B.M., Salim, S.I.B., Chuan, L.K. (2018) Fixed point implementation of tiny-yolo-v2 using opencl on fpga. keywords: computing; data; design; hardware; network; point; structure; yolov3 cache: fcis-14040.pdf plain text: fcis-14040.txt item: #128 of 872 id: fcis-14047 author: Yang, Leyan title: SafeCross: Helping Elder People Cross the Road Timely Using Thermal Imaging and Image Recognition date: 2023 words: 2532 flesch: 45 summary: Firstly, a large amount of thermal imaging and image data needs to be collected, including various scenarios and poses of elderly pedestrians crossing the road. With trained models, elderly pedestrians can be accurately detected and recognized, and their position and motion information can be extracted. keywords: image; imaging; recognition; road; system; time; traffic cache: fcis-14047.pdf plain text: fcis-14047.txt item: #129 of 872 id: fcis-14054 author: Gao, Yuru title: Image Retrieval based on Deep Learning date: 2023 words: 2085 flesch: 34 summary: Design and Training of Image Feature Extraction Network Image feature extraction network is the core component of image retrieval system, and its design and training are crucial to the performance and effect of image retrieval. The Main Content of the Paper The purpose of this study is to explore the development and application of image retrieval methods based on deep learning. keywords: feature; image; learning; methods; retrieval cache: fcis-14054.pdf plain text: fcis-14054.txt item: #130 of 872 id: fcis-14055 author: Zhong, Jing title: Using IGMP Protocol to Improve the Latency of Cloud Computing date: 2023 words: 2136 flesch: 63 summary: The normal way for a client to use cloud server to do the task is shown as Fig 1. Normal way for a client uses cloud server to do task As shown in Fig 2, on the client side, each client still must upload the original image to S3, because each client must assume themselves as the first uploader of the resource. keywords: client; cloud; network; server cache: fcis-14055.pdf plain text: fcis-14055.txt item: #131 of 872 id: fcis-14059 author: Tan, Songyin; Pu, Hongping title: Receiving ADS-B Signals on Embedded Linux using RTL-SDR: A Practical Guide date: 2023 words: 2691 flesch: 48 summary: It offers advantages such as flexibility, customizability, and low power consumption, making it ideal for building a variety of embedded systems. An overview of embedded systems for the 21st century[J] . keywords: ads; linux; rtl; sdr; system; technology cache: fcis-14059.pdf plain text: fcis-14059.txt item: #132 of 872 id: fcis-14562 author: Wang, Shihao; Wu, Xiangxiang title: The Mechanical Performance Prediction of Steel Materials based on Random Forest date: 2023 words: 2130 flesch: 46 summary: For example, machine learning algorithms are used to analyze and model large amounts of material data, predicting material performance indicators. Furthermore, research on mechanical properties drives the development of new materials, offering possibilities for innovation and the advancement of new fields. keywords: forest; materials; model; performance; steel; strength cache: fcis-14562.pdf plain text: fcis-14562.txt item: #133 of 872 id: fcis-14563 author: Chen, Lei; Zhou, Chao; Chen, Jianjun title: Power Quality Disturbance Recognition based on Deep Neural Network and Adaptive Feature Fusion date: 2023 words: 4538 flesch: 58 summary: [11] uses S-transform to extract the characteristics of power quality disturbance data and chaotic integrated decision tree algorithm to classify the disturbance. In literature [12], mRMR algorithm is used to extract the features of power quality disturbance data, and then multi- core SVM is used to classify the extracted disturbance features. keywords: accuracy; classification; data; disturbance; feature; layer; noise; power; quality; recognition cache: fcis-14563.pdf plain text: fcis-14563.txt item: #134 of 872 id: fcis-14566 author: Ou, Yining title: Dynamic Allocation Mechanism of Cloud Computing Resources Driven by Neural Network date: 2023 words: 2664 flesch: 44 summary: Dynamic resource allocation in cloud infrastructure using ant lion-based auto-regression model. This will help to improve the cost-effectiveness of resource allocation and better meet the needs of users. keywords: allocation; cloud; computing; mechanism; network; resource cache: fcis-14566.pdf plain text: fcis-14566.txt item: #135 of 872 id: fcis-14567 author: Jiang, Chunli; Chen, Guo title: Research and Analysis of Vegetable Pricing and Replenishment Decisions date: 2023 words: 4282 flesch: 53 summary: This data provides enough support to prove that there is correlation between vegetable categories and it is not likely to be caused by random factors. Under the constant change of market supply and demand, shopping malls need to consider the shelf life of vegetables, the rational use of sales space, and strive to get the maximum benefit of the situation to analyze the correlation between different categories of vegetables or different single products, to formulate the total amount of replenishment and pricing strategy is the way of survival of the superstore keywords: category; correlation; cost; data; eggplant; pricing; profit; sales; table cache: fcis-14567.pdf plain text: fcis-14567.txt item: #136 of 872 id: fcis-14568 author: Zhu, Honggu; Wu, Jiaye title: Classification Method for Railway Tunnel Secondary Lining Cold Joint Detection based on CNN-BiLSTM-SVM Model with Improved Hybrid Leader Algorithm date: 2023 words: 4417 flesch: 53 summary: As one of the methods of cold joints detection, the principle is that cold joints will change the energy and speed of Rayleigh waves [3], and cold joints are identified based on this characteristic. In the future, the data set can be gradually improved, a better fitness function can be designed, and through cross- validation, better SVM parameters can be obtained, the generalization ability of the model can be improved, and the detection accuracy can be further improved. keywords: algorithm; data; detection; function; hybrid; leader; model; optimization; svm cache: fcis-14568.pdf plain text: fcis-14568.txt item: #137 of 872 id: fcis-14569 author: Hou, Yingjie; Wang, Zhangang; Liu, Xu title: An Adaptive Multitasking Evolutionary Computation Offloading Algorithm for Mobile Edge Computing date: 2023 words: 6612 flesch: 47 summary: Based on the relevant research on the marginalization of computing resources, the European Telecommunications Standards Association proposed the concept of mobile edge computing. [6] X. Cao, F. Wang, J. Xu, R. Zhang, S. Cui, Joint computation and communication cooperation for mobile edge computing, 16th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt) (2018) 1– 6doi:10.23919/wiopt.2018.8362865. keywords: algorithm; area; computing; consumption; delay; devices; edge; energy; individuals; mobile; offloading; optimization; population; task cache: fcis-14569.pdf plain text: fcis-14569.txt item: #138 of 872 id: fcis-14570 author: Song, Haisheng; Zhang, Deyang title: Robot Path Planning Algorithm based on Improved A* and DWA date: 2023 words: 3128 flesch: 61 summary: Establishment of Environmental Model The prerequisite for robot path planning is to select an appropriate environment model. Reaching the end point safely proves the feasibility of the fusion algorithm in robot path planning. keywords: algorithm; node; obstacles; path; planning; point cache: fcis-14570.pdf plain text: fcis-14570.txt item: #139 of 872 id: fcis-14571 author: Tu, Zhenan title: Research on Vulnerabilities in Computer Information Technology and Encryption Techniques date: 2023 words: 3155 flesch: 32 summary: DES is a relatively older but classic encryption algorithm that uses a 56-bit key for data encryption. In other words, data security vulnerabilities encompass various vulnerabilities or weaknesses in computer systems or networks, which when exploited by malicious actors, pose uncertain and significant threats to information security. keywords: data; encryption; information; key; security; technology; vulnerabilities cache: fcis-14571.pdf plain text: fcis-14571.txt item: #140 of 872 id: fcis-14572 author: Dan, Yuanhong; Zhong, Haiyang title: Trajectory Tracking Control Algorithm of Two-wheel Rutting Model date: 2023 words: 3009 flesch: 66 summary: Unmanned two-wheelers are sensitive to wheel speed, and vehicle control constraints are set to make the vehicle run stably: 0.1 / 0.1 / 0.1 / 0.1 / r d r m s v v m s m s v m s         (24) Formula 10 belongs to the continuous equation of state, and it needs to be discretized before model predictive control keywords: control; k t; ref ref; t t; vehicle cache: fcis-14572.pdf plain text: fcis-14572.txt item: #141 of 872 id: fcis-1460 author: Li, Zhihui; Jia, Xiaoshuo title: DisCnet: Pixel segmentation based on discrete features date: 2022 words: 1858 flesch: 57 summary: DisCnet extracts the features with larger discreteness in the image by analyzing the distribution characteristics of discrete data, that is, edge features. The purpose It enhances the information of edge features on the one hand, and preserves the correlation between features on the other hand. keywords: discnet; edge; features; image; layer; segmentation cache: fcis-1460.pdf plain text: fcis-1460.txt item: #142 of 872 id: fcis-1461 author: Chu, Yan; Zhou, Zejiong title: Problems and Countermeasures of Green Finance Development under the Goal of "Double Carbon" in China date: 2022 words: 4378 flesch: 41 summary: First, banks should actively respond to policies and cooperate with government agencies; Secondly, we should innovate green financial products and services according to the investment and financing needs of green industry development; Thirdly, promote product innovation in the field of green finance, such as participating in the carbon emission trading market and exploring new carbon finance businesses such as carbon futures. Third, establish a green financial risk management mechanism, incorporate green financial risks into the comprehensive risk management system, implement differentiated control over customer access, monitoring and early warning, and improve the whole process risk management before, during and after loans; Finally, explore appropriate risk stress tests and scenario analysis, analyze and evaluate the possible risks of risk exposure under various scenarios, and enhance the bank's ability to cope with risks. keywords: carbon; china; development; finance; financial; goal; green; management; system cache: fcis-1461.pdf plain text: fcis-1461.txt item: #143 of 872 id: fcis-1462 author: Zhou, Ming title: The Digital Economy and the Regional Economic Gap: An Inverted U-shaped Relationship date: 2022 words: 8323 flesch: 39 summary: Based on the perspective of new economic geography, the digital economy is incorporated into the core marginal model, and the impact of digital economy development on the change of regional economic gap under long-term equilibrium conditions is deduced Provincial panel data are used to support this. The possible marginal contributions of this paper are: (1) to study the regional economic gap from the perspective of digital economy, and to explore the relationship between digital economy development and regional economic gap; (2) Incorporate the digital economy into the core-edge model from the perspective of influencing production costs and transaction costs, and explore the relationship between the digital economy and the regional economic gap under long-term equilibrium conditions with the help of computer simulation technology. keywords: development; digital; economy; economy development; effect; enterprises; gap; level; model; regional; regions; spatial cache: fcis-1462.pdf plain text: fcis-1462.txt item: #144 of 872 id: fcis-1463 author: Liu, Qinfeng; Zhang, Qianyu; Chen, Jialan; Wang, Tao title: Research on the effect of FOCUS-PDCA quality management on improving the maintenance and use of monitors in hospitals date: 2022 words: 3200 flesch: 36 summary: P(Plan)-To make the plan For the above improvement process plan, the implementation plan should be made, mainly including the following aspects :(1) CQI group members should develop training plans for equipment management and use, patient vital signs explanation and patient transfer process; (2) the CQI group formulated the daily management list of medical staff; (3) the CQI group should establish the annual implementtation plan of the three-level maintenance of medical devices; (4) the CQI group studied and established the implementation plan of quantitative assessment of medical devices management for medical staff. The effective maintenance and use management of monitors is an important part of medical equipment management keywords: hospital; improvement; maintenance; management; monitors; pdca; quality; use cache: fcis-1463.pdf plain text: fcis-1463.txt item: #145 of 872 id: fcis-1464 author: Zhang, Zehua; Huang, Ziheng title: Design and Application of Logistics Robot based on RPA date: 2022 words: 7660 flesch: 39 summary: Logistics information capture framework This framework aims at grasping logistics information in relevant documents, systems and databases, and grabbing relevant logistics data according to demand, including logistics system background information, in-and-out information, logistics order information, logistics status information and other data. The application of RPA robot in logistics management process. keywords: data; figure; framework; logistics; logistics information; logistics management; logistics system; management process; process; robot; rpa; rpa robot; system; time cache: fcis-1464.pdf plain text: fcis-1464.txt item: #146 of 872 id: fcis-1465 author: Liu, Yingxian title: Study on optimization of bus scheduling date: 2022 words: 2346 flesch: 48 summary: Overview of bus scheduling problem The main research content of this paper is mainly three parts, one is the data mining of public transportation big data, the second is to propose an improved genetic algorithm to solve the problem of intelligent bus scheduling, and the third is to develop the intelligent bus scheduling system. The optimization of bus scheduling can improve the service quality and benefit passengers, and also reduce the input cost of bus companies. keywords: algorithm; bus; bus scheduling; data; model; problem; scheduling cache: fcis-1465.pdf plain text: fcis-1465.txt item: #147 of 872 id: fcis-14686 author: Yao, Jerry; Zou, Yuan; Du, Shuqian; Wu, Hong; Yuan, Bin title: Progress in the Application of Artificial Intelligence in Ultrasound Diagnosis of Breast Cancer date: 2023 words: 2818 flesch: 42 summary: At present, the application of computer-aided detection methods in breast cancer ultrasound has been gradually promoted, and the combined application of artificial intelligence has played an advantageous role in the field of breast disease ultrasound diagnosis, such as shortening the examination time, effectively improving the detection rate and diagnostic accuracy rate. ROC curves were used to compare the mammogram findings of two doctors after CAD Research methods for benign and malignant tumor detection in breast ultrasound images are mainly divided into two categories: (1) Methods based on manual feature extraction: The gray scale symbiosis matrix was calculated by extracting the minimum boundary rectangular region around the lesion, and 22 symbiosis statistics were calculated from 6 quantization levels, 4 directions and 10 distances, respectively. keywords: breast; cancer; detection; diagnosis; features; intelligence; lesions; line; ultrasound cache: fcis-14686.pdf plain text: fcis-14686.txt item: #148 of 872 id: fcis-14690 author: Ren, Shuxia; Li, Simin title: Image Emotion Analysis Combining Attention Mechanism and Multi-level Correlation date: 2023 words: 5269 flesch: 51 summary: The CNN-based approach can learn features automatically through its multi-level deep learning architecture, rather than manually designing image features. After the forward LSTM model and the reverse LSTM model, the forward hidden feature th  and the reverse hidden feature th  are obtained for each layer of image features. keywords: analysis; attention; channel; emotion; features; image; level; method; model; visual cache: fcis-14690.pdf plain text: fcis-14690.txt item: #149 of 872 id: fcis-14697 author: Xu, Jingyu; Pan, Linying; Zeng, Qiang; Sun, Wenjian; Wan, Weixiang title: Based on TPUGRAPHS Predicting Model Runtimes Using Graph Neural Networks date: 2023 words: 3206 flesch: 50 summary: Model results data Accuracy train test tiles 0.8785 0.8622 Layout:xla:random 0.6841 0.5285 Layout:xla:default 0.5631 0.5887 Layout:nlp:random 0.8197 0.8387 Layout:nlp:default 0.5036 0.4841 These results reinforce the potential of advanced deep learning techniques, especially GNN models, to improve the accuracy of model runtime predictions. Various recent methodologies leverage machine learning (ML) to acquire performance prediction models. keywords: configuration; data; graph; layout; learning; machine; model; networks; node; performance; prediction; runtime cache: fcis-14697.pdf plain text: fcis-14697.txt item: #150 of 872 id: fcis-14812 author: Liu, Jiakang; Huo, Hua title: DFENet: Double Feature Enhanced Class Agnostic Counting Methods date: 2023 words: 5976 flesch: 54 summary: Specifically, the counting module receives the channel-level connections between query feature map  XF We extract two different levels of feature maps from the backbone network, which represent the low and medium level and high level features of the image, respectively. keywords: class; computer; counting; feature; image; information; maps; method; module; network; query; similarity; targets; vision cache: fcis-14812.pdf plain text: fcis-14812.txt item: #151 of 872 id: fcis-14826 author: Ren, Shuxia; He, Ning; Zhang, Xuanzheng title: A Joint Fake News Detection Model based on Multi-Features date: 2023 words: 6363 flesch: 56 summary: The next step of this research is to explore the characteristics of different dimensions of fake news detection (such as images, videos, voice, etc.), and combine multi- dimensional information in news to achieve a more comprehensive understanding of fake news and better detection ability. Additionally, our model obtains a Macro F1 Score of 0.904 on the latest COVID-19 dataset, demonstrating strong competitiveness and promising prospects for fake news detection. keywords: comment; detection; emotion; features; information; model; news; news detection; score; semantic; sentiment; stance; text cache: fcis-14826.pdf plain text: fcis-14826.txt item: #152 of 872 id: fcis-14841 author: Chen, Shuohan title: Tower Defense Game Design based on Unity3D date: 2023 words: 8236 flesch: 63 summary: Among them, tower defense games, as a branch of strategy games, have also been loved by the majority of players. Tower defense games don't have a long history among all types of games. keywords: attack; building; defense; defense game; design; function; game; game attack; interface; map; player; resources; soldier; target; tower; tower defense cache: fcis-14841.pdf plain text: fcis-14841.txt item: #153 of 872 id: fcis-14848 author: Cai, Weijie title: Analysis of Application Scenarios of Cloud Computing and Internet of Things Technology in Smart Cities date: 2023 words: 2627 flesch: 41 summary: In today's accelerating city digitalization development, the amount of city data maintains an exponential increase. This paper analyzes the key technology of smart city construction. keywords: city; cloud; construction; data; internet; smart; technology; things cache: fcis-14848.pdf plain text: fcis-14848.txt item: #154 of 872 id: fcis-14856 author: Zhang, Quan; Cai, Guoqing; Cai, Meiqing; Qian, Jili; Song, Tianbo title: Deep Learning Model Aids Breast Cancer Detection date: 2023 words: 2462 flesch: 48 summary: This nuanced exploration of diverse backbone architectures highlights the pivotal role of feature extraction in enhancing the overall performance of breast cancer detection models. Attention-based multi-NMF deep neural network with multimodality data for breast cancer prognosis model. keywords: analysis; breast; cancer; data; detection; feature; learning; model; pooling cache: fcis-14856.pdf plain text: fcis-14856.txt item: #155 of 872 id: fcis-14858 author: Zhou, Hong; Lou, Yan; Xiong, Jize; Wang, Yixu; Liu, Yuxiang title: Improvement of Deep Learning Model for Gastrointestinal Tract Segmentation Surgery date: 2023 words: 2445 flesch: 35 summary: As technology continues to evolve, the integration of automated segmentation models into clinical workflows holds the potential to make a substantial impact on cancer care, facilitating more efficient and tailored treatments for patients globally. Related Work Research in medical image segmentation, particularly in the context of oncology, has witnessed significant advancements driven by the integration of deep learning techniques. keywords: cancer; learning; model; mri; radiation; segmentation; stomach; therapy cache: fcis-14858.pdf plain text: fcis-14858.txt item: #156 of 872 id: fcis-14859 author: Zhang, Yating title: Research on the Market Development of Mongolian-Themed Films date: 2023 words: 3217 flesch: 39 summary: Through in-depth research on the Mongolian-themed film market, we explore its market-oriented development paths and strategies, and provide useful reference and guidance for the development of Mongolian films. Strengthen the training and introduction of Mongolian film talents and provide professional training and education opportunities. keywords: audience; development; films; market; movies; support cache: fcis-14859.pdf plain text: fcis-14859.txt item: #157 of 872 id: fcis-14861 author: Wang, Zhize title: Public Place Crowd Transaction Monitoring System date: 2023 words: 3230 flesch: 49 summary: For instance, the 2014 stampede incident at the Shanghai Bund highlights the criticality of monitoring abnormal crowd behaviors and crowd density in public spaces for everyone's safety. This paper proposes a deep learning-based method for detecting abnormal crowd behaviors using PyTorch. keywords: behaviors; crowd; data; density; detection; group; image; public; technology; video; vol cache: fcis-14861.pdf plain text: fcis-14861.txt item: #158 of 872 id: fcis-14888 author: Ye, Zewei; Zeng, Liwei; Wang, Qingzhang; Wang, Zhicheng; Cui, Jianhua; Cao, Yanning; Shen , Lingling; Qian, Xiaojun title: An Intelligent Equipment Inspection System based on Robotic Arm date: 2023 words: 2791 flesch: 50 summary: Introduction Nowadays, robotic arms have been widely used in production and life, such as manufacturing, intelligent service areas. Therefore, the intelligent inspection system for equipment based on robotic arm has become an important research direction to solve such problems. keywords: algorithm; arm; detection; motion; planning; rrt; system; target; yolo cache: fcis-14888.pdf plain text: fcis-14888.txt item: #159 of 872 id: fcis-14896 author: Xu, Feng; Cai , Xiaowei title: Interval Type Combination Prediction Model based on Improved Grey Correlation Degree IOWHA Operator date: 2023 words: 3123 flesch: 49 summary: Abstract: In order to improve the accuracy of interval number prediction, this paper proposes a new type of interval number combination prediction model based on improved grey correlation degree and IOWHA operator. To ensure the integrity of interval number sequences, interval number sequences are represented by centers and radii, interval number prediction accuracy is used as the inducing factor, and improved grey correlation degree is used as the optimality criterion to construct an interval type combination prediction model based on improved grey correlation degree and induced ordered harmonic weighted average (IOWHA) operator. keywords: interval; prediction; t t cache: fcis-14896.pdf plain text: fcis-14896.txt item: #160 of 872 id: fcis-1496 author: Tang, Huili title: Significance of identifying the location and nature of lesion in imaging diagnosis of diplopia date: 2022 words: 1791 flesch: 58 summary: A: Head CT scan showed abnormal lesion in the left cavernous sinus. In the second patient, the left abducens nerve was involved and gradually worsened, head CT showed abnormal lesions of the left cavernous sinus, MRI and CTA of the head showed a siphon aneurysm of the left internal carotid artery. keywords: disease; head; nerve; patient cache: fcis-1496.pdf plain text: fcis-1496.txt item: #161 of 872 id: fcis-1497 author: Luo, Zhengtian title: Graph Convolution Network Recommender Rystem with Feature Embedding date: 2022 words: 2821 flesch: 54 summary: NGCF[10] uses methods in GCN to extract information from the bipartite graph of user items, trains the model with this information to generate vectors of user items, and then uses these embeddings to make predictions. In this work, we combine the use of feature information with graph convolutional network to design a new recommendation algorithm, Graph Convolution Network recommender system with Feature Embedding, GCNFE. keywords: graph; information; items; layer; model; network; recommender; system; user cache: fcis-1497.pdf plain text: fcis-1497.txt item: #162 of 872 id: fcis-15071 author: Liu, Chang; Zhou , Xiangyang; Li , Jun; Ran, Chuantao title: PCB Board Defect Detection Method based on Improved YOLOv8 date: 2023 words: 3221 flesch: 51 summary: This, in turn, facilitates the subsequent feature fusion process and enhances the accuracy of model detection. Additionally, it enhances the region of interest by directing the model's focus towards the critical regions of defective small targets, thereby increasing the sensitivity of small target detection. keywords: attention; circuit; detection; figure; model; pcb; target; yolov8 cache: fcis-15071.pdf plain text: fcis-15071.txt item: #163 of 872 id: fcis-15072 author: Zhang, Lehan title: Research on the Application of Non-contact Sensing Technology in Real-time Emotional Monitoring and Feedback date: 2023 words: 2928 flesch: 39 summary: China Abstract: With the rapid development of information technology, non-contact sensing technology has shown great potential in the field of real-time emotional monitoring and feedback. First of all, we found that non-contact sensing technology effectively improved the objectivity of emotion monitoring. keywords: application; contact; monitoring; sensing; technology; time; users cache: fcis-15072.pdf plain text: fcis-15072.txt item: #164 of 872 id: fcis-15077 author: Chen, Zhimei title: Hardware Accelerated Optimization of Deep Learning Model on Artificial Intelligence Chip date: 2023 words: 2640 flesch: 37 summary: The focus of this paper is on the hardware acceleration optimization of deep learning model on AI chip, aiming at deeply discussing how to achieve efficient processing of deep learning tasks through clever design and optimization of hardware structure. This paper aims to explore the hardware acceleration optimization strategy of deep learning model on AI chip to improve the training and inference performance of the model. keywords: chip; computing; hardware; learning; model; optimization cache: fcis-15077.pdf plain text: fcis-15077.txt item: #165 of 872 id: fcis-15080 author: Zhang, Yuzhou title: Collaborative Optimization of Supply Chain Intelligent Management and Industrial Artificial Intelligence date: 2023 words: 2357 flesch: 22 summary: In this paper, the collaborative optimization of supply chain intelligent management and industrial AI is reasonably applied in daily work, so as to improve the efficiency and quality of management in an all-round way, and promote the common development of multi-agents while exerting the role of supply chain management and achieve product quality control through supplier supply of high- quality and high-performance components, and collaborative development and management with suppliers. By analyzing the influence of AI technology on supply chain information collaboration, the collaborative process is analyzed from the perspectives of logistics, inventory and procurement, which provides a new paradigm and reference for improving the automation and decentralization of supply chain information collaboration[8]. keywords: chain; enterprises; information; management; optimization; quality; supply cache: fcis-15080.pdf plain text: fcis-15080.txt item: #166 of 872 id: fcis-15089 author: Ye, Anning; Zhang, Min title: The Relationship between Social Responsibility and Brand Value of Chinese Food and Beverage Enterprises in the Context of High-Quality Development date: 2023 words: 5156 flesch: 41 summary: Some domestic scholars believe that there is no positive correlation between fulfilling corporate social responsibility and corporate brand value. Research has found that fulfilling corporate social responsibility has a negative impact on brand value enhancement, while technological innovation has a positive impact on brand value enhancement. keywords: beverage; beverage enterprises; brand; brand value; enterprises; food; impact; responsibility; social; value cache: fcis-15089.pdf plain text: fcis-15089.txt item: #167 of 872 id: fcis-15093 author: Zhou, Zejiong; Jiang, Yuting title: Comparison of R&D Input-Output Efficiency in 31 Provinces and Cities in China date: 2023 words: 3893 flesch: 41 summary: Therefore, this paper evaluates China's regional R&D input and output efficiency from both static and dynamic aspects by establishing the index system of R&D input and output with certain theoretical value, which is of practical significance for the improvement of regional R&D input and output efficiency and the in-depth implementation of the national innovation-driven strategy. 2. (1) From the comprehensive technical efficiency index, R&D input and output efficiency did not reach DEA efficiency in 2017 and 2021, and the supply efficiency was 0.41 and 0.386 respectively, which is in the lower category. keywords: drs; efficiency; innovation; input; output; provinces; r&d; r&d input; scale cache: fcis-15093.pdf plain text: fcis-15093.txt item: #168 of 872 id: fcis-15107 author: Wen, Lei title: SC-UneXt: Nested UNeXt Architecture based on Medical Image Segmentation date: 2023 words: 4123 flesch: 53 summary: At the same time, medical image segmentation provides a variety of effective methods for the accuracy and robustness of organ segmentation, lesion detection, and classification. Future research topics in medical image segmentation will be deep learning to automatically select features from different resolutions, or consider using adversarial training including test images to exploit features in test images without annotations. keywords: attention; edge; feature; fusion; image; information; loss; model; network; segmentation; unext cache: fcis-15107.pdf plain text: fcis-15107.txt item: #169 of 872 id: fcis-15114 author: Fu, Jiale; Li, Hongyan; Zhao, Yanxia; Zhang, Run; Zhang, Hejing; Pang, Taotao title: Research on Mining Talent Demand for E-commerce Majors based on LDA Topic Model date: 2023 words: 6196 flesch: 42 summary: Through the construction and optimization of LDA topic models, we can better mine the topic information in text data, providing a more reliable foundation for subsequent text analysis and decision-making. Fang F et al.[18] took the recruitment information for data analysis positions as an example, classified the skills requirements in different regions, and combined the clustering results of ability requirements text with salary, company size, and other information for analysis. keywords: analysis; commerce; data; experience; information; job; lda; model; network; positions; recruitment; requirements; text; topic; word cache: fcis-15114.pdf plain text: fcis-15114.txt item: #170 of 872 id: fcis-15121 author: Weng, Wei; Lin, Yifu; Wu, Jiawei title: Research on Establishing Inbound Strategies for Supermarkets based on LSTM and Gaussian Process Regression Modeling date: 2023 words: 2648 flesch: 50 summary: The significant advantages of the model include making full use of time series data and applying statistical analysis and visualization tools such as line plots, correlation matrices, Spearman coefficients, and heat maps to intuitively understand the data structure. Pie Chart of Sales Volume of Six Categories After that, in this paper, the major categories of vegetable sales are processed in time series to check whether the data has a significant periodicity or trend [1], and the six categories are sorted in chronological order through matlab output as shown in Figure. keywords: data; model; paper; pricing; sales; time; vegetable; volume cache: fcis-15121.pdf plain text: fcis-15121.txt item: #171 of 872 id: fcis-15176 author: Zhang, Ying; Xi, Lele; Wu, Yixia; Li, Canping; Ma, Zebin title: Algorithm Analysis and Design Python Teaching Example of Greedy and Dynamic Programming date: 2023 words: 1764 flesch: 59 summary: Although greedy algorithms sometimes do not lead to an optimal solution but to a near-optimal solution, they can greatly improve the efficiency of our solution within the error margin [3]. (2) Any topic that requires consideration of previously taken steps or paths is not suitable for the use of greedy algorithms. keywords: algorithm; problem; programming; solution cache: fcis-15176.pdf plain text: fcis-15176.txt item: #172 of 872 id: fcis-15183 author: Wei, Yalin title: Analysis of Spatial Diversity Technology based on MIMO Antenna Structures date: 2023 words: 3532 flesch: 42 summary: MIMO (Multiple-Input Multiple-Output) spatial diversity technology, based on the structure of MIMO antennas, is a system that uses multiple antennas for signal transmission. By using multiple transmitting antennas to split the transmitted signals into multiple signals and sending them out separately in space, transmit diversity can improve system stability, fault tolerance, and anti-interference capability. keywords: antennas; communication; data; diversity; mimo; signal; system; technology; transmission cache: fcis-15183.pdf plain text: fcis-15183.txt item: #173 of 872 id: fcis-15184 author: Zhang, Mingquan; Hu, Junwei; Wu, Zihao title: Analysis of Energy Consumption Optimization for Shared Cache Conflicts date: 2023 words: 2288 flesch: 44 summary: At present, the conflict constraint technology for multi-core shared cache is far from meeting the requirements of low energy consumption and low latency. Overall, the research on conflict constraint optimization for multi-core shared cache faces the main challenges: a) How to reduce the Bank conflict delay caused by multi- core and multi-cache partitions sharing the same Bank in the process of low-power shared cache partitioning, and achieve the minimization of Bank conflict delay; b) keywords: cache; conflict; consumption; core; energy; partitioning; time cache: fcis-15184.pdf plain text: fcis-15184.txt item: #174 of 872 id: fcis-15186 author: Li, Xunyang; Chen, Jin title: Optimization of Food Distribution System Based on Dynamic Planning Model date: 2023 words: 4185 flesch: 53 summary: Next, we consider the efficiency of food distribution. After the modeling framework is built, there is a specific problem; food distribution is not a simple allocation of resources; people in each region have a minimum standard of food needs, which cannot be based on evaluation indicators such as overall satisfaction and profitability. keywords: distribution; food; matrix; model; production; region; satisfaction; system cache: fcis-15186.pdf plain text: fcis-15186.txt item: #175 of 872 id: fcis-15189 author: Chen, Yanbin title: Exploration of Teaching Reform of Information Technology Fundamentals Course in Vocational Colleges based on Blended Teaching date: 2023 words: 2470 flesch: 33 summary: Due to the special nature of information technology basic course teaching, the course teaching platform and the course practical operation platform are usually located in different software. In response to the needs of information technology basic course online learning platforms, Tencent Classroom or DingTalk are usually used for live course teaching, The selection of a practical platform for the Wisdom Tree course facilitates students to access computer programming software. keywords: course; information; learning; students; teaching; technology cache: fcis-15189.pdf plain text: fcis-15189.txt item: #176 of 872 id: fcis-15192 author: Chen, Chen title: Digital Interactive Learning Method and its Influence on College Art Students’ Learning Satisfaction date: 2023 words: 2093 flesch: 41 summary: Furthermore, there is a significant direct relationship between the assessment of video-based learning effectiveness and student satisfaction with generic skills and learning experiences. Moreover, there is a significant difference in the assessments of both respondents on the effectiveness of virtual learning and overall digital interactive learning method, there is a significant difference in the satisfaction of assessment of the students among different year levels, and the fourth-year students have a significantly higher satisfaction compared to third year students. keywords: digital; learning; satisfaction; students cache: fcis-15192.pdf plain text: fcis-15192.txt item: #177 of 872 id: fcis-15197 author: Li, Jingang title: Eye Movement on Predicting Serve Return of College Female Tennis Players of Different Levels in Henan Province date: 2023 words: 2429 flesch: 44 summary: The independent sample T-test results of the prediction accuracy of the receiving point of the two groups of subjects F P t P Accuracy 0.175 0.679 -5.394 0.000 -5.384 0.000 *P<0.05 As can be seen from Table 4, the average prediction accuracy of professional group is higher, and the difference between groups is smaller; The average prediction accuracy of amateur group was lower, and the difference between groups was greater. Methods: In this study, 20 female tennis players from colleges and universities in Henan Province were randomly selected as professional group, and 20 female tennis students from colleges and universities in Henan Province were randomly selected as amateur group. keywords: amateur; fixation; group; time cache: fcis-15197.pdf plain text: fcis-15197.txt item: #178 of 872 id: fcis-15223 author: Yang, Xiaohui title: The Narrative Study of Guidance for Postgraduate Entrance Exams for Master's Students date: 2023 words: 3323 flesch: 23 summary: On this basis, internal meetings of the student union will be held to promptly provide feedback and address the learning and living issues of postgraduate students, in order to mobilize the work enthusiasm of the college student union and implement the purpose of serving students wholeheartedly in practice. Through the discussion and analysis of the postgraduate entrance examination environment, the handling of interpersonal relationships, and the personal significance of the examination, it is concluded that specialized tutoring for college students is a comprehensive consideration of the impact of the learning environment, dedicated to serving students, helping them resolve conflicts, overcome crises, establish and improve interpersonal relationships, and so on. keywords: college; education; entrance; entrance examination; examination; postgraduate; postgraduate entrance; students cache: fcis-15223.pdf plain text: fcis-15223.txt item: #179 of 872 id: fcis-15224 author: Shi, Leixi; Phakdeephirot, Nutteera title: Tiktok E-commerce User Stickiness Operation Strategy and Prospect date: 2023 words: 5751 flesch: 49 summary: User engagement and behavior: Researchers focus on user engagement on e-commerce live streaming platforms, including frequency, duration, and interactive behavior of watching live broadcasts. These data indicate that the number of online live streaming users in China is getting closer to the total number of netizens, and the number of e-commerce live streaming users is close to half of the overall number of netizens. keywords: behavior; commerce; development; industry; platforms; research; streaming; study; tiktok; users; video cache: fcis-15224.pdf plain text: fcis-15224.txt item: #180 of 872 id: fcis-15227 author: Jiao, Yulin; Xiao, Feng; Zhang, Wenjuan; Huang, Shujuan; Lu, Hao; Lu, Zhaoting title: Image Inpainting based on Gated Convolution and spectral Normalization date: 2023 words: 4348 flesch: 45 summary: It solves the problems of mode collapse and model training difficulty in the training of image inpainting model based on generative adversarial network. Since the generative adversarial network was proposed, a large number of Image inpainting models based on generative adversarial network have emerged in the field of image restoration, which have higher repair efficiency and better repair effect than traditional image restoration methods. keywords: convolution; discriminator; image; inpainting; layer; model; network; repair; restoration cache: fcis-15227.pdf plain text: fcis-15227.txt item: #181 of 872 id: fcis-15229 author: Chen, Nan title: Research on Ideological and Political Education into Front-End Development Courses date: 2023 words: 1986 flesch: 30 summary: Front end development courses are important courses for computer majors, and it is necessary to integrate ideological and political education into front-end development courses. 3. Course Ideological and Political Application Design keywords: courses; development; education; end; students cache: fcis-15229.pdf plain text: fcis-15229.txt item: #182 of 872 id: fcis-15232 author: Wu, Qingling title: Research on Collaborative Training Mechanism of Prefabricated Construction Talents in Higher Vocational Colleges under the Background of Integration of Production and Education date: 2023 words: 1640 flesch: 35 summary: Based on the integration of production and education, this paper discusses the cooperative training mechanism of prefabricated construction talents in higher vocational colleges, in order to provide useful reference for improving the quality of talent training. Through the in-depth cooperation of school-enterprise coordination, we can jointly develop talent training programs, optimize curriculum Settings, improve the construction of practical training bases, and constantly improve the quality of talent training. keywords: construction; industry; training cache: fcis-15232.pdf plain text: fcis-15232.txt item: #183 of 872 id: fcis-15262 author: Tang, Yongkang; Sun, Xiangguo title: Research on Voiceprint Recognition based on Densenet date: 2023 words: 3850 flesch: 57 summary: Due to the high security and the ability to collect speech features without user contact, the market share of voiceprint recognition has increased and is being applied to a wider range of fields. Similar to speech recognition, both require processing of speech signals to extract their features. keywords: densenet169; figure; gru; network; recognition; speaker; speech; voiceprint;   cache: fcis-15262.pdf plain text: fcis-15262.txt item: #184 of 872 id: fcis-15733 author: Li, Qinsheng; Shi, Qingfeng title: Research on Gymnastics Teaching and Training Simulation System under Computer Internet of Things Technology date: 2024 words: 2358 flesch: 37 summary: Users can view real-time updates of training data, historical trend analysis, and customized training plans through this interface. This feedback is based on the system's continuous analysis of training data, including instant assessment and improvement suggestions for movement execution. keywords: athletes; data; gymnastics; system; technology; training cache: fcis-15733.pdf plain text: fcis-15733.txt item: #185 of 872 id: fcis-15745 author: Tu, Tran Anh; Phuong, Pham Thi title: Research on Convolution Neural Network for Object Detection and Recognition date: 2024 words: 3897 flesch: 60 summary: Faster r-cnn: Towards real-time object detection with region proposal networks. Introduction Recently, advances in object detection are driven by progresses of backbone deep convolutional neu- ral networks keywords: cnn; detection; model; object; proposals; rectangle; region; truth cache: fcis-15745.pdf plain text: fcis-15745.txt item: #186 of 872 id: fcis-15749 author: Anh, Duong Duc; Tuan, Pham Duy; Hoan, Nguyen Quang; Vu, Nguyen Hong; Quang, Doan Hong; Quyen, Lai Thi Van title: Learning for Cellular Neural Networks Using the GARPLA Algorithm date: 2024 words: 3015 flesch: 56 summary: The GA for Cellular Neural Networks The genetic algorithm is a prominent method in evolutionary computing extensively used for addressing optimization challenges, particularly notable for its application in the field of neural networks [10], [11], [12]. Given that the computation of Cellular Neural Networks (CeNNs) involves a continuous optimization process, the adoption of the base-10 gene is particularly fitting. keywords: algorithm; cenns; learning; networks; neural; set; step; weight cache: fcis-15749.pdf plain text: fcis-15749.txt item: #187 of 872 id: fcis-15756 author: Teng, Zijian; Zhang, He title: Blowout Fluid Velocity Measurement Method based on High-speed Sequence Images date: 2024 words: 5934 flesch: 55 summary: Comparison of blowout fluid flow velocity and calibration flow velocity at different focal lengths From Table 4 and Figure 15, it can be concluded that when the camera focal length f=35mm, its flow rate value is relatively close to the calibrated flow rate value, and its calculation accuracy is the lowest at 94.06% and the highest at 96.95%; When the focal length of the camera is f=75mm, its flow rate value is closest to the calibrated flow rate value, and its calculation accuracy is the lowest at 96.89% and the highest at 98.45%. Blowout fluid image (a) (b) Fig 9. keywords: algorithm; blowout; blowout fluid; camera; feature; flow; fluid; https://www.webofscience.com/wos/alldb/general-summary?queryjson=%5b%7b; image; jet; matching; measurement; point; rate; system; velocity cache: fcis-15756.pdf plain text: fcis-15756.txt item: #188 of 872 id: fcis-15765 author: Song, Zhen; Wang, Jianxing title: A Survey of Monocular Depth Estimation based on Deep Learning date: 2024 words: 5517 flesch: 54 summary: Therefore, this paper provides an overview of current deep learning-based methods for monocular depth estimation. Finally, we discuss the challenges in monocular depth estimation and provide some ideas for future research. keywords: computer; conference; depth; depth estimation; estimation; ieee; image; learning; methods; monocular; network; training; vision cache: fcis-15765.pdf plain text: fcis-15765.txt item: #189 of 872 id: fcis-15776 author: Xiong, Wei; Zuo, Yue; Zhang, Menglin; Zhang, Chenxi; Guo, Caiqing title: Research on Sentiment Analysis of E-commerce Live Comments based on Text Mining date: 2024 words: 1879 flesch: 37 summary: However, with the rise of e-commerce live broadcasting, the comment information generated by a large number of users has also doubled, which contains rich emotional information.[1] The emotional information in e-commerce live comments carries consumers' attitudes and feelings towards products, services and shopping experience. In the field of e-commerce live broadcasting, sentiment analysis has become a research direction that has attracted much attention, providing profound user insight and commercial value for e-commerce enterprises.[4]A number of scholars have made positive contributions in this field, through various text mining techniques and sentiment analysis methods, in-depth research on the user emotion information contained in e-commerce live comments. keywords: analysis; comments; commerce; live; sentiment cache: fcis-15776.pdf plain text: fcis-15776.txt item: #190 of 872 id: fcis-15777 author: He, Chuan title: Design Scheme of High Concurrent and High Usable Cache based on TB Level Data Capacity date: 2024 words: 2379 flesch: 62 summary: Cache is generally divided into three categories: first is browser cache; second is server cache; third is cache in the network. There is a particularly clear difference between Redis cache and relational databases such as MySQL, because the former has faster IO and more efficient memory usage, and a significant increase in throughput and response speed. keywords: cache; data; database; request; server; system cache: fcis-15777.pdf plain text: fcis-15777.txt item: #191 of 872 id: fcis-15778 author: Ren, Yongchuan; Xie , Guofeng; Liu, Feng; Luo, Kaihuai; Chen, Tianxing title: Research on Secondary Development Method based on Haochen CAD date: 2024 words: 1787 flesch: 45 summary: Write VB program code, create Haochen CAD objects, and start running Haochen CAD. This approach allows applications to use Windows messaging mechanisms to send messages to Haochen CAD objects and directly call the core 43 functions of Haochen CAD[8]. keywords: arx; cad; development; haochen; object; secondary cache: fcis-15778.pdf plain text: fcis-15778.txt item: #192 of 872 id: fcis-15779 author: Chen, Ziyi; Qiu, Jingwen; Liu, Ziyu title: Research on Cooperation Mode and Evolution Analysis of Huawei Company based on Patent Collaboration Network date: 2024 words: 2065 flesch: 33 summary: Patent technology collaboration is a significant avenue for open innovation in enterprises, enabling rapid industrialization of achievements and strongly facilitating the acquisition, absorption, and utilization of external resources. Beijing accounts for the highest number of patent collaborations, which is associated with the location of key collaborative partners (such as the Institute of Computing Technology of the Chinese Academy of Sciences, Tsinghua University, etc.) in Beijing. keywords: collaboration; huawei; network; patent; research; technology cache: fcis-15779.pdf plain text: fcis-15779.txt item: #193 of 872 id: fcis-15780 author: Zhang, Xiang title: Exploration of the Role of Human-computer Interaction Technology in Collaboration and Communication in Work Scenarios date: 2024 words: 3274 flesch: 30 summary: It covers various technological means, such as natural language processing, gesture recognition, virtual reality, etc., aiming to achieve more humanization, efficiency, and usability of computers in HCI[1]. HCI technology is not limited to a single technical field, but is a comprehensive interdisciplinary research that includes multiple fields such as computer science, psychology, anthropology, and design. In office scenarios, HCI technology provides an intuitive and efficient interface, making office software more user-friendly and improving employee work efficiency. keywords: communication; computer; human; interaction; members; team; technology; work cache: fcis-15780.pdf plain text: fcis-15780.txt item: #194 of 872 id: fcis-15781 author: Li, Shulin; Yu, Liqiang; Liu, Bo; Lin, Qunwei; Huang, Jiaxin title: Application Analysis of AI Technology Combined with Spiral CT Scanning in Early Lung Cancer Screening date: 2024 words: 2817 flesch: 54 summary: In the process of diagnosing small pulmonary nodules, low-dose CT scan can quickly scan the overlapping lesions of mediastinum and diaphragm, and perform high-resolution multi-plane reconstruction to obtain clear images of small pulmonary nodules. Wang Wei et al. pointed out that due to the small diameter of pulmonary nodules, routine examination is not of high diagnostic value, which is prone to misdiagnosis and missed diagnosis, causing delay in early treatment of the 53 disease and affecting the quality of life of patients. keywords: cancer; diagnosis; early; image; lung; nodules; technology; window cache: fcis-15781.pdf plain text: fcis-15781.txt item: #195 of 872 id: fcis-15809 author: Zong, Yanqi; Cui , Zhengrong; Lin, Luqi; Wang, Sihao; Chen, Yizhi title: An Overview of the Development of Stereotactic Body Radiation Therapy date: 2024 words: 4210 flesch: 45 summary: Abstract: Stereotactic body radiation therapy (SBRT) refers to focusing high-energy rays in three-dimensional space on the tumor lesion area, reducing the dose received by surrounding normal tissues, which can effectively improve the local control rate of the tumor and reduce the probability of complications. Dose assessment of stereotactic body radiation therapy for primary liver cancer based on 4D-CT image sets. keywords: body; dose; position; radiation; radiotherapy; stereotactic; technology; time; treatment; tumor cache: fcis-15809.pdf plain text: fcis-15809.txt item: #196 of 872 id: fcis-15810 author: Pan, Yiming; Shen, Zepeng; He, Yuhang; Wei, Kuo; Zhang, Yuchen title: Application of Three-dimensional Coding Network in Screening and Diagnosis of Cervical Precancerous Lesions date: 2024 words: 3574 flesch: 46 summary: Based on domestic and foreign research results, this paper will discuss the application of artificial intelligence in cervical cancer screening and diagnosis from the four aspects of HPV detection, cytology, colposcopy, and imaging examination, and propose the challenges faced by artificial intelligence in cervical cancer screening and diagnosis in the future [1][2][3]. This paper will discuss the application of AI in cervical cancer screening and diagnosis from four aspects: HPV detection, cytology, colposcopy, and imaging. keywords: cancer; convolution; diagnosis; feature; information; layer; map; model; module; network; screening cache: fcis-15810.pdf plain text: fcis-15810.txt item: #197 of 872 id: fcis-15811 author: Gao, Guokang; Li, Yue title: Based on Hierarchical Reinforcement Learning for Large-scale Pedestrian Trajectory Prediction date: 2024 words: 4548 flesch: 48 summary: It considers the advantages of hierarchical reinforcement learning and divides the complete process of pedestrian trajectories at the airport into layers. A large-scale pedestrian trajectory planning algorithm based on hierarchical reinforcement learning is designed to match the hotspots in the airport region simulated by pedestrian trajectories with congested areas in the terminal scene. keywords: agent; airport; hierarchical; number; pedestrian; process; reinforcement; simulation; terminal; time cache: fcis-15811.pdf plain text: fcis-15811.txt item: #198 of 872 id: fcis-15812 author: Zhong, Chenhui title: Artificial Intelligence and Malicious Code Detection date: 2024 words: 2520 flesch: 38 summary: In this work, we propose a CNN convolutional neural network-based method for detecting malicious code. This article presents the construction of a deep learning training model for CNN designed to identify malicious code. keywords: article; cnn; code; detection; learning; machine; sandbox; software cache: fcis-15812.pdf plain text: fcis-15812.txt item: #199 of 872 id: fcis-15813 author: Ren, Hanpeng; Dong, Lei; Jin, Yangang; Zheng, Yuefei; Zhu, Haojie; Zhao, Beiping; Feng, Yushuang title: Study on the Lightweighting of YOLOv5s Model for Precise Detection of Irregular-shaped Components date: 2024 words: 3561 flesch: 50 summary: This modification results in a lighter network with reduced model parameters and size, thereby improving detection speed. In conclusion, the enhanced model (model C) surpasses the original YOLOv5 model in mAP, recall, and model size. keywords: algorithm; cbs; detection; model; module; network; parts; precision; recognition; vision cache: fcis-15813.pdf plain text: fcis-15813.txt item: #200 of 872 id: fcis-15814 author: Zhao, Xinyu; Liu, Bo; Lin, Qunwei; Huang, Jiaxin; Yu, Liqiang title: Effective Combination of 3D-DenseNet's Artificial Intelligence Technology and Gallbladder Cancer Diagnosis Model date: 2024 words: 2608 flesch: 48 summary: For example, Wu Shi yang et al first segmtioned lung cancer CT images in the lung image database Consortium to obtain lung nodule images, then used Convolutional Neu-ral Network (CNN) for feature extraction, and finally used Logistic classifier for model construction and testing. 2)The interpretability of deep learning model has been criticized for a long time. keywords: cancer; densenet; detection; diagnosis; gallbladder; image; layer; learning; medical; model cache: fcis-15814.pdf plain text: fcis-15814.txt item: #201 of 872 id: fcis-15815 author: Li, Yiming title: CSI-based WIFI Device Identification Solution date: 2024 words: 6480 flesch: 54 summary: In recent years, more and more authentication schemes based on device fingerprints have been proposed. (2) Stability: The stability of device fingerprints over time and place. keywords: antennas; csi; data; detection; device; error; fig; fingerprint; hardware; network; phase; rap; rpe; wifi; wireless cache: fcis-15815.pdf plain text: fcis-15815.txt item: #202 of 872 id: fcis-15816 author: He, Zheng; Chen, Wangmei; Zhou, Yanlin; Weng, Huiying; Shen, Xinyu title: The Importance of AI Algorithm Combined with Tunable LCST Smart Polymers in Biomedical Applications date: 2024 words: 3013 flesch: 44 summary: Temperature- sensitive polymers exhibit changes in structure or solubility with temperature, with the temperature at which these changes occur referred to as the transition temperature. While the definition of smart polymers can include two-phase transition processes such as glass transition and melting, the focus of research in the field of smart polymer systems is their behavior in polymer aqueous solutions, interfaces, and hydrogels. keywords: ccsp; dega; drug; lcst; materials; pega; polymer; solution; temperature cache: fcis-15816.pdf plain text: fcis-15816.txt item: #203 of 872 id: fcis-15817 author: Yang, Weiping; Huang, Chao title: A License Plate Detection and Recognition Method Based on Improved Yolov5 date: 2024 words: 2740 flesch: 49 summary: Conclusion In license plate detection and recognition, due to the limitations of the working environment, mobile embedded devices are more suitable for detection tasks. Through experiments, we found that the model in this study is more suitable for license plate detection and 99 recognition tasks, achieving a good balance in terms of accuracy and speed. keywords: accuracy; detection; license; model; network; plate; recognition; yolov5 cache: fcis-15817.pdf plain text: fcis-15817.txt item: #204 of 872 id: fcis-15820 author: Qian, Jili; Song, Tianbo; Zhang, Quan; Cai, Guoqing; Cai , Meiqing title: Analysis and Diagnosis of Hemolytic Specimens by AU5800 Biochemical Analyzer Combined with AI Technology date: 2024 words: 2799 flesch: 41 summary: Abstract: There is a close correlation between biochemical analysis instruments and artificial intelligence, in biomedical engineering, biochemical analysis instruments produce a large number of complex data, including spectral data, mass spectrometry data, electrochemical data, etc. Introduction The Automatic Biochemical Analyzer AU5800 is a highly advanced clinical laboratory instrument that is highly automated and can automate a variety of biochemical analysis and assay processes, including the analysis of blood, urine and body fluid samples. keywords: analysis; analyzer; blood; concentration; data; detection; hemoglobin; hemolysis; samples cache: fcis-15820.pdf plain text: fcis-15820.txt item: #205 of 872 id: fcis-15824 author: Yang, Hao; Zhang, Huifu; Gong , Ziyi title: Computation Offloading and Resource Allocation in Mobile Edge Computing-enabled IoT Network date: 2024 words: 7477 flesch: 53 summary: Furthermore, from Figure 5, we can deduce easily that offloading computation tasks to the edge for execution is more advantageous when the amount of IoT UDs is higher. It should be noted that this study exclusively focuses on local task execution or offloading to MEC servers, without considering additional offloading to remote centralized clouds or other ENs. keywords: computation; computing; edge; edrl; energy; execution; iot; learning; mec; network; offloading; system; task cache: fcis-15824.pdf plain text: fcis-15824.txt item: #206 of 872 id: fcis-15825 author: Pan, Weihua; Nie, Mengying title: Intelligent Pavement Diseases Detection Model based on YOLOv5s date: 2024 words: 3994 flesch: 50 summary: At the early stage, pavement diseases detection was mainly based on manual detection, which was time-consuming and laborious, and the detection efficiency was low, so it could not meet the large-scale road detection task. As a result, although YOLOv5s model has been widely used in pavement diseases detection, there are still some problems, such as false detection, missed detection and low accuracy of small target detection. keywords: attention; data; detection; diseases; information; model; network; pavement; road; yolov5s cache: fcis-15825.pdf plain text: fcis-15825.txt item: #207 of 872 id: fcis-15826 author: Zheng, Jiajian; Yang, Le; Xin, Duan; Tian, Miao title: The Credit Card Anti-fraud Detection Model in the Context of Dynamic Integration Selection Algorithm date: 2024 words: 3134 flesch: 48 summary: For credit card transaction data, histograms can be used to analyze the distribution of transaction amounts. 1. Collect credit card transaction data: Collect normal credit card transaction data, including transaction amount, transaction time and other information. keywords: algorithm; anomaly; card; credit; data; detection; fraud; histogram; set; transaction cache: fcis-15826.pdf plain text: fcis-15826.txt item: #208 of 872 id: fcis-15827 author: Fu, Guanyu title: Automatic Pricing and Replenishment Decision for Vegetable Products based on Planning Model and Regression Algorithm date: 2024 words: 2554 flesch: 46 summary: Results of correlation analysis of total sales volume of vegetables by category It can be concluded that there is a correlation between the total sales of different categories of vegetables, with a highly significant positive correlation between the total sales of vegetables in the cauliflower and foliar categories, and a highly significant negative correlation between the total sales of vegetables in the aquatic rootstocks and eggplant categories. Relationship between total sales volume and cost-plus pricing of different vegetable categories Vegetable category Regression results Significance (P) Foliage y=6641.387- 1628.304x 0.466 0.000 Cauliflower y=3702.895- 140.822x 0.611 0.004 Aquatic Roots y=4495.651- 269.121x 0.480 0.001 Eggplant y=1039.492- 10.922x 0.490 0.000 Edible fungi y=-673.860- 1538.585x 0.680 0.000 Capsicum y=3139.355- 49.520x 0.740 0.001 keywords: correlation; pricing; replenishment; sales; vegetable; volume cache: fcis-15827.pdf plain text: fcis-15827.txt item: #209 of 872 id: fcis-15828 author: Chen , Jianfeng; Xiong, Jize; Wang, Yixu; Xin, Qi; Zhou, Hong title: Implementation of an AI-based MRD Evaluation and Prediction Model for Multiple Myeloma date: 2024 words: 3620 flesch: 47 summary: Introduction Rapid pharmacological and technological developments in recent years can greatly reduce early mortality and improve survival rates in MM patients, significantly improving the prognosis of MM patients. These staging systems combine serological and genetic factors reflecting disease burden to stratify MM patients to assess their prognosis. keywords: bone; cell; image; marrow; mrd; myeloma; patients; signal; technology cache: fcis-15828.pdf plain text: fcis-15828.txt item: #210 of 872 id: fcis-15829 author: Duan, Shiheng; Liu, Yuxiang; Li , Linxiao; Pan, Yiming title: Prediction of Atmospheric Carbon Dioxide Radiative Transfer Model based on Machine Learning date: 2024 words: 3547 flesch: 39 summary: Based on the basic radiation model: Line-By-Line Radiative TransferModel (LBLRTM), the US National Center for Atmospheric Environmental Research (NCAR) developed the rapid radiative transfer model RRTMS, It simulates and calculates atmospheric radiation transfer through the parameterization of atmospheric radiation flux and heating rate. b. Treatment of radiation transfer equation the former can deal with multiple scattering processes, and the role of scattering is ignored in this model. keywords: atmospheric; calculation; data; learning; model; radiation; radiative; rrtmg; transfer; wave cache: fcis-15829.pdf plain text: fcis-15829.txt item: #211 of 872 id: fcis-15830 author: Song, Tianbo; Zhang, Quan; Cai, Guoqing; Cai, Meiqing; Qian, Jili title: Development of Machine Learning and Artificial Intelligence in Toxic Pathology date: 2024 words: 3650 flesch: 41 summary: The development and application of a wide variety of algorithms for histopathology suggests that AI pathology platforms can profoundly influence the future of digital toxic pathology, precision medicine, and personalized medicine. However, as with all other revolutionary technologies, there are many challenges in the implementation and application of AI pathology platforms. keywords: application; data; deep; development; digital; image; intelligence; learning; pathology; technology cache: fcis-15830.pdf plain text: fcis-15830.txt item: #212 of 872 id: fcis-16170 author: Yi, Yanan; Sun, Mingge title: Research and Simulation of Fuzzy Expert Anti-surge Control System for Compressor date: 2024 words: 2886 flesch: 65 summary: Due to the need for parameter tuning in both synchronous frequency conversion and fuzzy PID control, the combination of the two makes parameter adjustment more difficult; Fang Lin A method combining fuzzy PID control with expert PID control is proposed to address the flexibility issue of parameter adjustment in the compressor control system mentioned above. keywords: compressor; control; pid; ps ps; zo ps; zo zo cache: fcis-16170.pdf plain text: fcis-16170.txt item: #213 of 872 id: fcis-16178 author: Wang, Shuke; Xu, Yan title: A Focused Analysis of the Intersection of Machine Learning and Intelligent Decision date: 2024 words: 5237 flesch: 59 summary: Mach Lean 9.20 1996 2004 ▂▂▂▂▂▂▃▃▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂ 8 Classification Regre 8.35 1997 2016 ▂▂▂▂▂▂▂▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▂▂▂▂▂ 9 AI Mag 6.43 1996 2017 ▂▂▂▂▂▂▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▂▂▂▂ 10 Neural Networks Comp 6.25 2001 2014 ▂▂▂▂▂▂▂▂▂▂▂▃▃▃▃▃▃▃▃▃▃▃▃▃▃▂▂▂▂▂▂▂ 11 Appl Artif Intell 5.67 1999 2008 ▂▂▂▂▂▂▂▂▂▃▃▃▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂ 12 Adv Knowledge Discov 3.94 2000 2006 ▂▂▂▂▂▂▂▂▂▂▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂ Next, we examine the reference relationships between ML and ID from 1990 to 2021 and construct a visual reference network through CiteSpace to further elaborate the reference relationships, displayed in Figure 9. Top 12 cited authors with the strongest citation bursts from 1990 to 2021 Rank Cited Strength Begin End 1990-2021 1 Quinlan JR 18.94 1990 2014 ▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▂▂▂▂▂▂▂ 2 Mitchell TM 15.32 1994 2013 ▂▂▂▂▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂ 3 Vapnik VN 11.16 2005 2014 ▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▃▃▃▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂ 4 Goldberg DE 7.70 2003 2013 ▂▂▂▂▂▂▂▂▂▂▂▂▂▃▃▃▃▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂ 5 Zadeh LA 6.82 2002 2018 ▂▂▂▂▂▂▂▂▂▂▂▂▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▂▂▂ 6 Guyon I 5.71 2012 2018 ▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▃▃▃▃▃▃▃▂▂▂ 7 Burges CJC 5.16 2005 2014 ▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▃▃▃▃▃▃▃▃▃▃▂▂▂▂▂▂▂ 8 Michalski RS 5.13 1994 2004 ▂▂▂▂▃▃▃▃▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂ 9 Dietterich TG 5.12 2007 2018 ▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▃▃▃▃▃▃▃▃▃▃▃▃▂▂▂ 10 Fayyad U 4.39 2000 2016 ▂▂▂▂▂▂▂▂▂▂▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▃▂▂▂▂▂ 11 Kohonen T 4.33 2009 2012 ▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂ 12 Joachims T 4.18 2007 2012 ▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂ Table 5 provides information on the top 12 most frequently cited journals over the period from 1990 to 2021 that have been cited most frequently over a certain period. keywords: analysis; field; learning; machine; research; university; ▂ ▂; ▂ ▃; ▃ ▂; ▃ ▃ cache: fcis-16178.pdf plain text: fcis-16178.txt item: #214 of 872 id: fcis-16179 author: Wu, Shihao title: Behavior Prediction of Vespa mandarinia based on Convolutional Neural Networks date: 2024 words: 2859 flesch: 45 summary: Similarly, in addition to a prediction of the number of Vespa mandarinia and their dispersal routes, there is a need to identify Vespa mandarinia images for some uncertain and undetected sighting swarms. wish_542@163.com Abstract: Vespa mandarinia poses a significant threat to honey bees and beekeepers. keywords: control; hornet; mandarinia; model; network; number; vespa; vespa mandarinia cache: fcis-16179.pdf plain text: fcis-16179.txt item: #215 of 872 id: fcis-16180 author: Zhou, Qun title: PPBRFL: Privacy-Preserving Byzantine-Robust Federated Learning date: 2024 words: 5276 flesch: 59 summary: Furthermore, we introduce a reward and penalty mechanism that considers users’ behavior to mitigate the impact of Byzantine users on the global model. Byzantine users can upload false parameters to the cloud server, thereby compromising global model’s accuracy or manipulating the global model to produce specific outputs through poisoning attacks [10]. keywords: accuracy; classification; cloud; cosine; learning; model; ppbrfl; privacy; scheme; server; similarity; users cache: fcis-16180.pdf plain text: fcis-16180.txt item: #216 of 872 id: fcis-1624 author: Wang, Fumin title: Yolov5-based fall detection algorithm for homebound people date: 2022 words: 2272 flesch: 61 summary: Keywords: Yolov5s; Fall detection; Deep learning. Specifically, for fall detection, most of the existing algorithms are based on wearable devices [5], which are not ideal in terms of complexity and recognition capability. keywords: algorithm; detection; fall; figure; network; structure; yolo cache: fcis-1624.pdf plain text: fcis-1624.txt item: #217 of 872 id: fcis-1625 author: Xia, Nan; Xie, Jingwen; Yuan, Yucheng; Cao, Qifan; Li, Deyu title: Research on the Influence of Digital Economy on Rural Governance date: 2022 words: 4559 flesch: 37 summary: (3) Make full use of the unique data structure elements and information platform of the digital economy, stimulate the endogenous power of rural digital economy development, focus on breaking the digital barriers between cities and villages, improve the Internet coverage in rural areas, and improve the phenomenon of information poverty in some areas. Therefore, in the process of giving full play to the driving role of the digital economy in rural governance, we should pay attention to its promoting role and create a new pattern of rural digital governance. keywords: analysis; china; data; development; economy; governance; index; indicators; level; table; value cache: fcis-1625.pdf plain text: fcis-1625.txt item: #218 of 872 id: fcis-1626 author: Wang, Huimin; Hu, Xiaofeng; Xie, Xining title: Research progress on electrostatic discharge law of aircraft and radiation signal detection technology date: 2022 words: 6207 flesch: 37 summary: The analysis results show that the research hotspots of aircraft electrostatic discharge effect and static detection technology focus on the new mechanism of electrostatic discharge and new radiation signal detection technology brought about by new materials, new environments, new loads and new requirements, and the work that needs to be focused on urgent research mainly includes the study of the integrated characteristics of multi-source electrostatic discharge of aircraft, the long-distance detection of electrostatic discharge information, and the evaluation method of the effect of electrostatic discharge on the airborne electronic system, etc., which provide technical support for improving the reliability and safety of aircraft during flight. In this paper, from the aspects of the harm of electrostatic discharge to aircraft, the characteristics and radiation laws of electrostatic discharge of aircraft, and the detection technology of electrostatic signal of aircraft, this paper expounds the research progress at home and abroad, analyzes the new problems faced by the electrostatic discharge effect of aircraft and static detection technology, and looks forward to the next research and development direction. keywords: aircraft; characteristics; current; detection; discharge; discharge effect; discharge radiation; electric; field; flight; radiation; radiation field; research; signal; surface; system; technology cache: fcis-1626.pdf plain text: fcis-1626.txt item: #219 of 872 id: fcis-1627 author: Yu, Jiayi; Sun, Lifei title: Research on Goods Transportation Tracking System Based on Internet of Things date: 2022 words: 2721 flesch: 16 summary: Current Technology With the rapid development of economic globalization, the supply of raw materials between enterprises and the timely feedback of goods transportation information between businesses and consumers affect whether the transaction between enterprises and consumers can be carried out smoothly. China Abstract: The present disclosure relates to a goods transportation tracking system based on the Internet of things, including: the delivery terminal is used to obtain the loading information of logistics goods, the loading information includes the license plate number of the transport vehicle, the transportation route is determined according to the delivery address and receiving address of the logistics goods, and the distribution information including the license plate number and the transportation route is sent to the server; The server is used to determine the target high-speed monitoring terminal from the high-speed monitoring terminal according to the transportation route in the distribution information, generate acquisition instructions according to the license plate number, and send the acquisition instructions to the target high-speed monitoring terminal; The high-speed monitoring terminal is used to receive the acquisition instructions sent by the server, collect the license plate number of the transport vehicles within the monitoring range, and send the target tracking information to the server when the license plate number is collected; The server is also used to generate logistics information according to the target tracking information and push the logistics information to the delivery terminal and user terminal. keywords: information; logistics information; monitoring terminal; speed monitoring cache: fcis-1627.pdf plain text: fcis-1627.txt item: #220 of 872 id: fcis-1628 author: Hong, Yuer title: Research on the impacts of Philanthropy Pressure on Enterprise Financial Performance date: 2022 words: 4525 flesch: 46 summary: The results show 24 that ROA is significantly positively correlated with region and industry philanthropy pressure at 5% and 1% levels respectively, indicating that region philanthropy pressure will positively affect enterprise financial performance and industry philanthropy pressure will positively affect enterprise financial performance. While when faced with industry philanthropy pressure, firms are more likely to focus on industry stakeholders, customers and suppliers. keywords: enterprise; giving; government; industry; journal; level; performance; philanthropy; pressure; region; visibility cache: fcis-1628.pdf plain text: fcis-1628.txt item: #221 of 872 id: fcis-1629 author: Liu, Yanfei; Ning, Kanglin title: Multi-Stage Transformer 3D Object Detection Method date: 2022 words: 3088 flesch: 64 summary: References [1] Y. Zhou and O. Tuzel, ‘Voxelnet: End-to-end learning for point cloud based 3d object detection’, in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. [15] Z. Li, Y. Yao, Z. Quan, W. Yang, and J. Xie, ‘Sienet: spatial information enhancement network for 3d object detection from point cloud’, ArXiv Prepr. keywords: detection; detectors; encoder; method; object; point; stage; transformer cache: fcis-1629.pdf plain text: fcis-1629.txt item: #222 of 872 id: fcis-1630 author: Ren, Weiliang; Liao, Guibing; Zhang, Fuxing; Yang, Jingtao; Li, Jiayu; Li, Jie title: Design of Intelligent Control Arm Strength Training Device for Students date: 2022 words: 3510 flesch: 62 summary: During the use of the arm strength training device, only a single way of arm strength training can be carried out, and the complete and comprehensive training of arm strength, wrist strength, biceps and triceps muscles and other muscle groups cannot be carried out, and the training effect is not good, The training function is single; In the process of using arm strength training device, unreasonable placement, inconvenient folding, occupying large space, easy to collide with objects, and in the process of arm strength training, the tension adjustment of the training device is inconvenient, which can not meet various training needs, and the scope of application is narrow. Please refer to the operation process for the specific use method, the upper end is connected with the upper end of the tension rod and the lower end is connected with the upper and lower ends of the tension rod, the grip is made of plastic material, which is used for arm strength training by pulling a pull rope. keywords: end; rod groove; screw rod; support rod; support seat cache: fcis-1630.pdf plain text: fcis-1630.txt item: #223 of 872 id: fcis-16913 author: Xu, Minghong title: Flexible Job-shop Scheduling Optimization based on Improved Gray Wolf Algorithm date: 2024 words: 2353 flesch: 56 summary: Improved genetic algorithm for solving flexible job shop scheduling problem with multiple time constraints. [8] Qu, P., Tang, X. (2022) Improved particle swarm algorithm for flexible shop scheduling problem. keywords: algorithm; gwo; optimization; prey; scheduling; wolves cache: fcis-16913.pdf plain text: fcis-16913.txt item: #224 of 872 id: fcis-16914 author: Wang, Wenjun title: Research on Data Security and Privacy Protection in the Context of Big Data date: 2024 words: 4468 flesch: 41 summary: In 1987, Miller emphasized the importance of personal data protection and proposed early frameworks for data privacy designed to 30 ensure the appropriate use of data and prevent unauthorized data leakage[5]. Nonetheless, the technology was insufficient to protect data privacy at that time and remains an important research topic today. keywords: challenges; data; encryption; future; privacy; protection; quantum; research; security; technologies cache: fcis-16914.pdf plain text: fcis-16914.txt item: #225 of 872 id: fcis-16916 author: Rao, Kangwei title: Research on Preventing Medical Information from Leaking based on Homomorphic Encryption date: 2024 words: 3502 flesch: 33 summary: [6] In medical information encryption, homomorphic encryption can be used to calculate and analyze medical data without decrypting the data, thus protecting the privacy of the data. Next, we explore the specific application scenarios of medical information encryption, such as electronic medical records, medical images and encryption protection during transmission. keywords: algorithm; data; encryption; information; key; privacy; security cache: fcis-16916.pdf plain text: fcis-16916.txt item: #226 of 872 id: fcis-1701 author: Pan, Xiaofei title: Time series data anomaly detection based on LSTM-GAN date: 2022 words: 1475 flesch: 55 summary: Abstract: With the improvement of modern technology, a large number of time series data have been produced. The anomaly detection of time series data can provide relevant information for key situations faced by various fields. keywords: anomaly; data; detection; generator; model cache: fcis-1701.pdf plain text: fcis-1701.txt item: #227 of 872 id: fcis-1702 author: Wen, Qifan; Ji , Xiaofei title: Cigarette box code recognition based on machine vision date: 2022 words: 2477 flesch: 52 summary: After the expansion operation, the edges of image regions may become smooth, the number of pixels in the region will increase, and disconnected parts may be connected, all of which are the opposite of the erosion operation. 3)Open computing After the expansion operation, the edges of image regions may become smooth, the number of pixels in the region will increase, and disconnected parts may be connected, all of which are the opposite of the erosion operation. keywords: image; operation; recognition; region; training cache: fcis-1702.pdf plain text: fcis-1702.txt item: #228 of 872 id: fcis-1703 author: Zhang, Xu; Zhang, Xi title: Battery management system of UAV Based on IOT date: 2022 words: 1814 flesch: 54 summary: This system provides a new idea for the research of battery management system. In the charging protection circuit, the system monitors the input voltage and current in real time, adds two bq771807dpjr overvoltage protectors to prevent excessive charging voltage, and completes the shutdown of charging MOSFET Q24 and Q25 through the software configuration register when the charging voltage and current are greater than the set protection threshold, so as to prevent overcharging of lithium battery pack during charging and reduce the performance of battery pack. keywords: battery; management; module; system; time; voltage cache: fcis-1703.pdf plain text: fcis-1703.txt item: #229 of 872 id: fcis-17032 author: Wei, Yating; Yang, Lulu; Zhou, Jiajia; Wen, Rongchao; Chen, Xiangjiao; Jin, Xiong; Ye, Zhiyang title: Industrial Material Liquid Level Control System based on PLC date: 2024 words: 3768 flesch: 57 summary: According to the requirements of an enterprise for liquid level control of glycerine, this paper changes the traditional liquid level control mode to PLC control, improves the reliability, safety and visualization of the whole working process, makes the transmission control system has strong function and high reliability, and can be applied to the industrial field when combined with hardware. When the system starts, the PLC is transmitted to MCGS D14 South tank liquid level value input Liquid level of south tank signal input D15 South tank liquid level Display liquid level value of south tank D24 System1 tank liquid level value input Liquid level of system1 tank signal input D25 System1 tank liquid level Display liquid level value of system1 tank D34 North tank liquid level value input Liquid level of south tank signal input D35 North tank liquid level Display liquid level value of north tank D44 System2 tank liquid level value input Liquid level of system2 tank signal input D45 System2 tank liquid level Display liquid level value of system2 tank 43 Figure 6. keywords: level; limit; liquid; north tank; south; switch; system; tank; tank liquid cache: fcis-17032.pdf plain text: fcis-17032.txt item: #230 of 872 id: fcis-1704 author: Zhu, Rongrong; Zhang, Xiaofang title: Efficient incentive mechanism for video distribution on the home Internet of Things devices date: 2022 words: 4924 flesch: 58 summary: [12] supports dis- tributed data-intensive applications through close interaction between resources, supports field data-intensive application deployment through location-aware data placement, replica- tion, and recovery, and utilizes edge resources. [18] proposed that the response time of modern websites can be reduced by generating dynamic web content on edge nodes close to ending users. keywords: computing; content; devices; distribution; edge; mechanism; node; reputation; resources; time cache: fcis-1704.pdf plain text: fcis-1704.txt item: #231 of 872 id: fcis-17045 author: Wang, Lijie; Liang, Xiyin; Liang, Qi title: Design of Pseudo-random Sequence Generator based on Three-dimensional Discrete Chaotic System date: 2024 words: 5897 flesch: 47 summary: In this paper, a pseudo-random sequence generator with better randomness is constructed through the targeted improvement of chaotic system. The chaotic sequences generated by chaotic systems are inextricably linked with cryptography, and thus the pseudorandom sequences generated by chaotic systems have become a hot issue in current research keywords: analysis; design; figure; generator; paper; pseudo; sequence; system cache: fcis-17045.pdf plain text: fcis-17045.txt item: #232 of 872 id: fcis-17158 author: Zhou, Yu; Wang, Guijuan; Wu , Yadong; Zhang, Weihan title: Evaluation and Prediction of Sustained Competitive Advantage of Baijiu Enterprises Based on Entropy Weight-TOPSIS and INGO-BP Neural Network date: 2024 words: 8879 flesch: 46 summary: To enhance the objective and effective evaluation of sustained competitive advantage, financial indicators (development ability, profitability, solvency, operating ability, and cash flow) are integrated, alongside non-financial indicators (brand value, environment, and social responsibility), forming a systematic approach for assessing listed liquor companies. The study employs the entropy value method to calculate weighted indicators, followed by the TOPSIS method for a comprehensive evaluation of sustained competitive advantage. keywords: advantage; algorithm; development; enterprises; entropy; evaluation; goshawk; liquor; method; model; network; neural; northern; number cache: fcis-17158.pdf plain text: fcis-17158.txt item: #233 of 872 id: fcis-17185 author: Shang, Meiling; Qu, Rongguo; Ji, Deqing; Yu, Zhenxing; Fan, Qinwei title: Extreme Learning Machine Classification Method based on Twin Strategy Salp Swarm Algorithm date: 2024 words: 3481 flesch: 53 summary: However, due to the random generation of input layer weights and thresholds in ELM, it may result in unnecessary or suboptimal weights and thresholds. In order to mitigate the impact of the randomness in the input weights and thresholds of the Extreme Learning Machine (ELM) model, this paper proposes a Twin Strategy Salp Swarm Algorithm (TSSA) to optimize the input weights and thresholds of ELM. keywords: algorithm; elm; extreme; input; layer; learning; salp; swarm; weights cache: fcis-17185.pdf plain text: fcis-17185.txt item: #234 of 872 id: fcis-17186 author: Yang, Kaifang; Yang, Dewei; Wang, Fen; Zhao, Jing; Fan, Qinwei title: Entropy Error-based Convolutional Neural Network Sparse Optimization and Application date: 2024 words: 2024 flesch: 38 summary: Structured pruning of convolutional neural networks via L1 Regularization, IEEE Access, 7 (2019): 106385-106394. Convergence of deep convolutional neural networks, Neural Networks, 153 (2022): 553-563. keywords: function; layer; network; regularization cache: fcis-17186.pdf plain text: fcis-17186.txt item: #235 of 872 id: fcis-1722 author: Qi , Zefan title: Large-scale Aerosols Visualization Based on the Accelerated Ray Casting Algorithm date: 2022 words: 2574 flesch: 55 summary: It draws volume data in a 3D scalar data field into a 2D image through scientific computing by tracing rays from the viewpoint to the object. Volume data sub-components 4.2.1. keywords: algorithm; bounding; casting; data; ray; rendering; time; volume cache: fcis-1722.pdf plain text: fcis-1722.txt item: #236 of 872 id: fcis-17318 author: Yan, Tong title: Research on the Application of BIM in the Operation and Maintenance Management of University Libraries date: 2024 words: 3447 flesch: 29 summary: For example, data sharing between library management systems and human resources systems can make personnel scheduling more efficient. In summary, research on the application of BIM technology in library management systems has put forward requirements for data integration and standardization, equipment and facility modeling, intelligent operation and maintenance management, improvement of reader service quality, system integration and compatibility, data security and privacy protection. keywords: bim; library; maintenance; management; module; operation; system; technology cache: fcis-17318.pdf plain text: fcis-17318.txt item: #237 of 872 id: fcis-17319 author: Tan, Hui; Wu, Shenghong; Dai, Yunjie; Li, Yang; Feng, Youqin title: Artificial Intelligence Technology in Mechanical Dogs date: 2024 words: 2133 flesch: 45 summary: Firstly, this paper explains the development status of artificial intelligence technology (AI) at home and abroad, then gives an overview of AI technology and mechanical dogs respectively, then lists the application status of four common types of intelligent mechanical dogs, and finally concludes that AI technology in the field of mechanical dogs still has a better development prospect. With this background, this paper discusses the application of artificial intelligence technology in the field of mechanical dogs. keywords: development; dog; dogs; intelligence; robot; technology cache: fcis-17319.pdf plain text: fcis-17319.txt item: #238 of 872 id: fcis-17394 author: Liu, Qiong; Liu, Xueyan; Wang, Jia; Sun, Hao title: ES Data Aggregation Scheme based on Personalized Local Differential Privacy date: 2024 words: 4534 flesch: 55 summary: LDP can add noise to all data and effectively protect data privacy. In 2019, the ULDP model [10] provided a feasible method to reduce the protection of non-sensitive data according to the privacy requirements of different data, thereby improving data utility and protecting the privacy of sensitive data. keywords: data; privacy; uoue; utility cache: fcis-17394.pdf plain text: fcis-17394.txt item: #239 of 872 id: fcis-17407 author: Qin, Yucheng; Jiang, Tengfei; Xie, Mei'e title: Research on Intelligent Logistics Application based on Blockchain Technology date: 2024 words: 2843 flesch: 35 summary: The design and implementation of intelligent logistics system based on blockchain technology needs to comprehensively consider technical architecture, business model, user experience and other aspects, which breaks the limitations of traditional logistics industry and significantly improves operational efficiency.[5] The intelligent logistics system architecture based on blockchain technology includes the following levels. [9] Mao Zelong A transportation information management system and method based on logistics blockchain keywords: blockchain; data; industry; information; logistics; system; technology cache: fcis-17407.pdf plain text: fcis-17407.txt item: #240 of 872 id: fcis-17464 author: Lou, Ying; Chen, Wenhui title: Research on The Construction of Big Data Supervision Platform for Public Power in Universities date: 2024 words: 4462 flesch: 22 summary: Construction of Big Data Supervision Platform for Public Power in Universities The construction of big data supervision platform for university public power is one of the important ways to improve the efficiency of university public power supervision This paper will discuss the status quo and problems of university public power supervision, the construction of university public power big data supervision platform, as well as the challenges, problems, and countermeasures of platform construction. keywords: colleges; data; management; power; public; supervision; universities cache: fcis-17464.pdf plain text: fcis-17464.txt item: #241 of 872 id: fcis-17465 author: Song, Haisheng; Liu, Nian title: Research and Analysis of Dark Channel Priori Dehazing Algorithm based on Guided Filtering date: 2024 words: 3119 flesch: 55 summary: Notably, guided image filtering preserves the edges of the transmittance image, thereby enhancing its clarity and ultimately facilitating the generation of high-quality dehazed images.[7][8]. This normalization process allows for the enhancement of image contrast, even in situations where the original image exhibits low contrast characteristics.[6]. keywords: algorithm; channel; dark; filtering; image cache: fcis-17465.pdf plain text: fcis-17465.txt item: #242 of 872 id: fcis-17466 author: Yang, Jie; Li, Zijun title: Construction of a Climate Early Warning System: Predicting Future Temperatures and Climate Security Using BiLSTM date: 2024 words: 7075 flesch: 55 summary: A pause in the rise of global surface temperatures during the 2000s led some scholars to believe that global warming had been interrupted. BiLSTM has not yet been applied to predict the future trend of global land surface temperature. keywords: bilstm; climate; consumption; data; doi; energy; future; growth; model; prediction; rate; research; surface; temperature; vol; warning cache: fcis-17466.pdf plain text: fcis-17466.txt item: #243 of 872 id: fcis-1763 author: Xu, Yixuan title: Review and prospect of research on indoor positioning methods date: 2022 words: 1663 flesch: 39 summary: Nowadays, outdoor positioning has been basically solved systematically, and indoor positioning technology has become a research hotspot at home and abroad in recent years due to its complex environment and other factors. At present, common indoor positioning technologies mainly include WiFi positioning technology, Bluetooth positioning technology, ultra-wideband (UMB) positioning technology, geomagnetic fingerprint positioning technology, radio frequency identification (RFID) positioning technology, 4G/5G mobile communication network positioning technology, and radar positioning technology. keywords: indoor; method; positioning; target; technology cache: fcis-1763.pdf plain text: fcis-1763.txt item: #244 of 872 id: fcis-17637 author: Lu, Lei; Gao, Ran; Pan, Wei; Tang , Wenming title: A Point Cloud Contour Extraction Method based on Plane Segmentation date: 2024 words: 2982 flesch: 68 summary: The method involves fusing the random sample consensus (RANSAC) algorithm and principal component analysis (PCA) for plane segmentation, thereby enhancing the robustness and accuracy of point cloud plane segmentation. The alpha shape algorithm proposed by Herbert Edelsbrunner et al. is a scattered contour extraction algorithm, which can be applied to the extraction of polygon inner and outer contour points, but for point clouds with large data volume, the time complexity of the algorithm is high [10]. keywords: boundary; cloud; contour; extraction; method; plane; point cache: fcis-17637.pdf plain text: fcis-17637.txt item: #245 of 872 id: fcis-17679 author: Li, Ruixin; Pu, Hongping title: Study of Trajectory Filtering Methods for ADS-B Based on VSIMM-RSRCKF date: 2024 words: 2160 flesch: 43 summary: Model set updating definition , , ⋯ , is the total model set describing the system, based on the target state estimation at the (k-1) moment and the information of the model set at the (k-1) moment to delete invalid models and update the model set , where ∈ , ∈ . denotes the model that matches the target movement during this time, ∈ denotes the model that matches model s during this time, denotes the transfer probability of model s, and denotes the transfer probability of model s during the k moment. VSIMM algorithm model set and probabilistic transfer matrix can be variable according to the target's movement, terrain and other factors, etc., and different model sets are used under different conditions, which not only improves the system's computational efficiency but also ensures that the selected model matches the system's movement. keywords: ads; algorithm; filtering; model; rsrckf cache: fcis-17679.pdf plain text: fcis-17679.txt item: #246 of 872 id: fcis-1768 author: Fu, Hai title: Research on a UUV Cluster Communication Model date: 2022 words: 2106 flesch: 41 summary: To solve this problem, we use the advantages of network coding technology in traditional routing multicast, and apply network coding technology to underwater multi UUV cluster communication network to adapt to the scene of limited underwater communication bandwidth. At the same time, with the relay transmission of UUV nodes, data transmission between underwater UUV clusters and ships, air planes, space satellites, ground receiving stations and other underwater communication nodes can also be realized. keywords: cluster; communication; transmission; underwater; uuv cache: fcis-1768.pdf plain text: fcis-1768.txt item: #247 of 872 id: fcis-1773 author: Wang, Peizheng; Wang, Xie title: Blockchain-based Communication Mechanism for Unmanned Aircraft date: 2022 words: 3130 flesch: 50 summary: This paper first introduces the current situation and challenges of unmanned aircraft and blockchain, and proposes a communication mechanism for unmanned aircraft based on blockchain technology to achieve unmanned aircraft data security and privacy protection, multi-party data sharing and data storage security to ensure unmanned aircraft network security. With a centralised management mechanism, it is difficult to recover quickly from an attack, so there is an urgent need to design a decentralised storage mechanism to guarantee the safe storage of unmanned aircraft data. keywords: aircraft; blockchain; data; mechanism; network; nodes; security; technology; transaction cache: fcis-1773.pdf plain text: fcis-1773.txt item: #248 of 872 id: fcis-1774 author: Zhang, JiaPeng title: Design and Implementation of Insurance Product Recommendation System date: 2022 words: 3123 flesch: 38 summary: Recommendation system based on singular value decomposition and multi-objective immune optimization[J]. As shown in Table 1, the system divides the user's interest in the product degree into different behavioral association scores (-1 to 5 points), the higher the score, the higher the user's interest in the product, through the extraction of the user's behavior log to obtain the user's behavior score of the product, based on the recorded log data through the LDA-ALS algorithm model data calculation for personalized product recommendations. keywords: algorithm; als; data; insurance; recommendation; recommendation system; system; time; user cache: fcis-1774.pdf plain text: fcis-1774.txt item: #249 of 872 id: fcis-17871 author: Wang, Xinchong; Wang, Xinxiang title: Optimizing the Sales Law and Replenishment Decision Analysis of Fresh Supermarket Products date: 2024 words: 2383 flesch: 55 summary: Trend of total sales price of vegetables by category in supermarkets 31 From Figure 2, we can see that the sales volume of vegetable categories in supermarkets will fluctuate due to the influence of time and month, in which the sales volume of leafy vegetables has the largest fluctuation in these nine seasons, and the peak sales period is generally in the fall and winter, and edibles are also usually found in the fall and winter, so their sales volume in the spring and summer seasons are lower. Figure 3 below shows the trend of total sales price and average unit price for each category of vegetables in supermarkets in a quarterly cycle. keywords: category; pricing; sales; vegetable cache: fcis-17871.pdf plain text: fcis-17871.txt item: #250 of 872 id: fcis-17883 author: Huang, Qianru; Dong, Qingmei; Liu, Yunlong; Ji, Deqing; Fan, Qinwei title: A Sigma-Pi-Sigma Neural Network Model with Graph Regularity Term date: 2024 words: 2321 flesch: 68 summary: L f W X X     The initial weight 0W is given, and the iterative updates of the weights of the SPSNNGR algorithm are as follows: 1 1, 2 ,m m mW W W m     and ( )m m WW E W  . where  is the learning rate. 0 1( , , , )T T T T Q NP NW W W W    keywords: j j; network; sigma cache: fcis-17883.pdf plain text: fcis-17883.txt item: #251 of 872 id: fcis-17976 author: Lou, Zongzhi; Chen, Linlin; Guo, Tian; Wang, Zhizhong; Qiu, Yuxuan; Liang, Jinyang title: Target Detection and Segmentation Technology for Zero-shot Learning date: 2024 words: 4564 flesch: 43 summary: This is mainly due to the limited ability of ZSL models to generalize to new categories. The realization of this concept will theoretically break the limitation of existing learning models that rely entirely on a large amount of annotated data, making the computer vision system more flexible and intelligent. keywords: categories; detection; information; learning; model; research; segmentation; shot; zsl cache: fcis-17976.pdf plain text: fcis-17976.txt item: #252 of 872 id: fcis-17985 author: Tian, Xue; Wang, Xia; Li, Ying title: Analysis of Health Data for the Elderly based on Medical Website Mining date: 2024 words: 2641 flesch: 52 summary: However, due to the subjectivity in the process of manual word segmentation, there may also be some errors in word segmentation. The idea of word segmentation in this paper is as follows: 500 records are randomly selected as test data, and the remaining data are training data. keywords: data; health; medical; mining; segmentation; topic; word cache: fcis-17985.pdf plain text: fcis-17985.txt item: #253 of 872 id: fcis-18126 author: Wang, Zehan title: Information Extraction and Knowledge Map Construction based on Natural Language Processing date: 2024 words: 2683 flesch: 37 summary: [8] Zhang C, Mayr P, Lu W, et al. Guest editorial: Extraction and evaluation of knowledge entities in the age of artificial intelligence[J]. Through information extraction technology, the knowledge points scattered in the text can be extracted, which provides a data basis for the subsequent knowledge map construction. keywords: construction; entity; extraction; information; knowledge; map; relationship cache: fcis-18126.pdf plain text: fcis-18126.txt item: #254 of 872 id: fcis-18128 author: Liang, Yitao; Dai, Jiabei; Lu, Lei title: Three Dimensional Reconstruction of Two-step Moving Objects based on Phase-shifting Profilometry date: 2024 words: 2550 flesch: 56 summary: Most dynamic measurements require projecting multiple stripe patterns to obtain sufficient object phase information, and the more stripes there are, the greater the phase error caused by motion. By tracking object motion and analyzing the impact of motion on phase information, the phase change relationship caused by object motion between the phase shift fringe phase distribution and the low-frequency fringe phase distribution is obtained. keywords: motion; object; phase; reconstruction cache: fcis-18128.pdf plain text: fcis-18128.txt item: #255 of 872 id: fcis-18139 author: Jia, Yizhao; Qin, Lihao; He, Dan; Li, Na title: Research on Abnormal Behavior Detection Technology for Simmental Cattle date: 2024 words: 3674 flesch: 27 summary: Technical route of cattle abnormal behavior detection In terms of model improvement, the use of advanced neural network structures, such as deep residual networks and attention mechanisms, can improve the representation and perception capabilities of the model. (3) Laboratory animal studies: In laboratory animal studies, Simmental cattle abnormal behavior detection technology can be used to monitor the behavior patterns of laboratory animals, such as activity, eating, sleeping, etc. keywords: animal; behavior; cattle; data; detection; model; monitoring; technology; time cache: fcis-18139.pdf plain text: fcis-18139.txt item: #256 of 872 id: fcis-18356 author: Wen , Zilu; Liu, Jinyu; Liu, Chenxi title: Football Momentum Analysis based on Logistic Regression date: 2024 words: 3165 flesch: 53 summary: For example, a high positive coefficient for p1_swr means that the winning streak is positively correlated with winning match points when Player 1 has a winning streak. For example, Player 1's winning streak (p1_cwr) has a high positive coefficient, which indicates that when Player 1 scores consecutive points, this is positively associated with winning match points. keywords: match; model; momentum; performance; player; point; rate; winning cache: fcis-18356.pdf plain text: fcis-18356.txt item: #257 of 872 id: fcis-18357 author: Wang, Zhiwei; Wang, Min title: Research on Improved Algorithm for Small Object Detection in Intelligent Surveillance Video based on YOLOv7 date: 2024 words: 3589 flesch: 40 summary: Researchers are also exploring the integration of more context information and prior knowledge to assist in small object detection, as well as developing more complex multi-task learning frameworks to simultaneously perform object detection, classification, and tracking.[9] Overall, the field of small object detection in intelligent video surveillance is rapidly evolving, with new technologies and methods being proposed to address existing challenges. [2] Deep learning frameworks, especially Convolutional Neural Networks (CNNs), have become the mainstream method for small object detection. keywords: attention; cbam; detection; feature; model; network; object; yolov7 cache: fcis-18357.pdf plain text: fcis-18357.txt item: #258 of 872 id: fcis-1837 author: Zhang, Yan; Wu , Xianxian title: Multi-Purpose Portable Wireless Thermal Printer date: 2022 words: 2459 flesch: 61 summary: Thermal printing requires no ink and is fast. With the rise of artificial intelligence and the Internet of Things, thermal printing will usher in new market growth points in education and training, entertainment, healthcare and other fields, because these industries need more and more convenient, efficient, fast, low-cost image and text presentation and long-term preservation methods [2,3]. keywords: chip; control; figure; head; motor; print; printer; printing cache: fcis-1837.pdf plain text: fcis-1837.txt item: #259 of 872 id: fcis-18456 author: Zheng, Yuancheng; Ren, Hongwei title: Research of ESPI Stripe Skeleton Line Extraction Based on Improved Fast Parallel Algorithm date: 2024 words: 2365 flesch: 53 summary: In this paper, a fast parallel refinement algorithm for ESPI streak image is proposed for the commonly used ZS and OPTA fast parallel refinement algorithms, which improves the deletion template and retention template. The refinement of ESPI image plays an important role in the extraction of stripe information based on the stripe center method, and also plays a key role in the accurate interpretation of the electron scattering interference fringe pattern[3]. keywords: algorithm; image; pixel; refinement; skeleton; template cache: fcis-18456.pdf plain text: fcis-18456.txt item: #260 of 872 id: fcis-18462 author: He, Jian; Teng, Wei; Zhao, Zeyu; Liu, Binche; Qin, Bing; Jiang, Jun title: Research on the Detection of Traffic Flow based on Video Images date: 2024 words: 3508 flesch: 53 summary: Although some algorithms also adopt multi-scale feature fusion to carry out target detection, they often only use the features of one scale obtained after fusion. In the area of target detection, there are four types of samples: true positive(TP), false positive(FP), true positive(TP), false positive(FP), in order to quantify the performance comparison of the proposed network with other networks, this paper uses typical evaluation metrics such as precision (P) and recall (R), the formula is as follows: The average precision (AP) is the area below the P-R curve, which is the average of the Precision values of the P-R curve. keywords: accuracy; algorithm; detection; image; network; target; traffic; yolov5 cache: fcis-18462.pdf plain text: fcis-18462.txt item: #261 of 872 id: fcis-18501 author: Wang, Ying title: Media Safety Threshold for the Digital Protection and Inheritance of Dunhuang Culture: -- Take NFT Technology as an Example date: 2024 words: 3434 flesch: 23 summary: This requires using blockchain technology to establish an NFT platform dedicated to Dunhuang cultural digital resources. A core resource database should also be established for Dunhuang cultural digital resources. keywords: art; cultural; culture; digital; dunhuang; nft; resources; technology; transaction cache: fcis-18501.pdf plain text: fcis-18501.txt item: #262 of 872 id: fcis-18503 author: Wang, Wencheng; Wu, Quandi; Zhang, Pengcheng; Liu, Tianci title: Design of a Detachable Surface Garbage Cleaning Robot Suitable for Small Water Areas date: 2024 words: 3615 flesch: 54 summary: At present, the methods used to clean up water garbage mainly include mechanical and manual cleaning. Research on surface garbage cleaning devices started early in developed countries, where the technology is mature, multiple series have been developed, and it has become a major means of protecting urban water environments in these countries. keywords: cleaning; collection; garbage; hull; resistance; robot; surface; surface garbage; water cache: fcis-18503.pdf plain text: fcis-18503.txt item: #263 of 872 id: fcis-1871 author: Lei, Qinchuan; Chen, Nan; Ding, Shanren title: Curriculum syllabus reform from the perspective of engineering education professional certification: -- "WeChat Platform Development" course as an example date: 2022 words: 1838 flesch: 42 summary: Keywords: Engineering Education Certification; Course reform; WeChat platform development. At present, the research based on undergraduate engineering education mainly starts from its basic orientation, the basic requirements of professional education, the proposal of relevant standards and the design of relevant courses. keywords: course; education; engineering; reform; teaching cache: fcis-1871.pdf plain text: fcis-1871.txt item: #264 of 872 id: fcis-18731 author: Chen, Junwei; Cao, Ludan title: AI-enabled Rendering Technology for the Construction and Development of Dunhuang Virtual Pavilion date: 2024 words: 3985 flesch: 37 summary: In the context of AI technology applied to indoor rendering and Dunhuang virtual scenes, it is necessary to carry out the corresponding institutional innovation and construction. Cross-border collaboration of AI in indoor rendering and Dunhuang virtual scenes brings new opportunities for education and training, such as building virtual classrooms and learning platforms. keywords: application; cultural; dunhuang; experience; image; rendering; research; scene; technology; virtual cache: fcis-18731.pdf plain text: fcis-18731.txt item: #265 of 872 id: fcis-18737 author: Wu, Hanhan; He, Rongpeng; Dou, Tao title: Research on Speech Denoising Algorithm for Equipment Trains in Fully Mechanized Mining Working Faces based on CEEMDAN High and Low Frequency Filtering date: 2024 words: 3372 flesch: 54 summary: Although wavelet transform to achieve noise reduction in specific environments, it is necessary to manually select the wavelet base and noise reduction threshold according to the differential noise in different environments, which lacks adaptability. Therefore, the high and low frequency filtering algorithm based on CEEMDAN proposed in this article has good application value for noise reduction of speech signals acquired in the train environment of fully mechanized mining face equipment, and is beneficial to improving the accuracy of subsequent speech recognition. keywords: algorithm; ceemdan; coal; equipment; frequency; kalman; low; noise; signal cache: fcis-18737.pdf plain text: fcis-18737.txt item: #266 of 872 id: fcis-18738 author: Wan, Xiaohe title: Energy-Saving Design Strategies in Electrical Engineering Automation Systems: Towards an Environmentally Friendly Society date: 2024 words: 3706 flesch: 22 summary: This paper analyzes the structure of electrical engineering automation systems, the characteristics of these systems, and the principles followed in energy-saving designs within electrical engineering automation. The Principle of Energy Saving Design in Electrical Engineering Automation System In the context of promoting energy conservation, emission reduction, and sustainable development, the energy-saving design of electrical engineering automation systems has become an important research area. keywords: automation; design; efficiency; energy; engineering; power; system cache: fcis-18738.pdf plain text: fcis-18738.txt item: #267 of 872 id: fcis-18739 author: Xu, Yuhang title: Application of Image Segmentation Algorithms in Computer Vision date: 2024 words: 2444 flesch: 39 summary: This article delves into the research and application of image segmentation algorithms in CV, with a focus on the application of DL in the field of image segmentation. Image segmentation is not only a crucial transitional step from image processing to image analysis, but also a hot and difficult research topic in the field of CV. keywords: algorithms; feature; image; segmentation; technology cache: fcis-18739.pdf plain text: fcis-18739.txt item: #268 of 872 id: fcis-1883 author: Zhan, Zhenrun; Bi, Xiaodan; Yang, Jinpeng; Zhao, Tingting title: Research Progress on the effect of calcium overload on myocardial ischemia-reperfusion injury date: 2022 words: 3938 flesch: 45 summary: A large number of literatures have proved that calcium overload occurs during myocardial ischemia reperfusion, and calcium overload can further aggravate myocardial ischemia reperfusion injury. Therefore, we can conclude that sodium hydrogen exchanger is an important part of calcium overload mechanism, and we can reduce reperfusion injury through it. keywords: ca2; calcium; cells; injury; ions; ischemia; mechanism; overload; reperfusion; sodium cache: fcis-1883.pdf plain text: fcis-1883.txt item: #269 of 872 id: fcis-1884 author: Ling, Fengru; Gong, Shu title: Research on Project-Based Learning Python Programming Course date: 2022 words: 2382 flesch: 45 summary: Exception Week 6~10 VI Query/statistics module design: find students information by students' name/ID; query and display all students' information; count the total number of students as above Week 11 VII Sorting module design: display students' information in ascending or descending order according to the grades of each subject or all subjects as above Week 12 VIII Project Packaging: Package the program as an executable file (*.exe) Installation and use of modules; Python built-in module: os Organization of project documents: first-level file: project folder; secondary files: Python files (to achieve specific functions), files (to save student information) automatically created by the system Week 3 IV Main function design: write the main function to display the main interface functions of the system Variables and Data types; Input and output; Process control; Call of function Week 4~5 V Design of student information maintenance module: input, delete, modify student information. keywords: course; knowledge; learning; programming; project; students; teaching cache: fcis-1884.pdf plain text: fcis-1884.txt item: #270 of 872 id: fcis-1885 author: Su, Jinfeng; Ying, Liu; Li, He; Ning, Bian title: Exploration of Huawei Advanced Network Technology Curriculum Reform under the Background of School enterprise Cooperation date: 2022 words: 2027 flesch: 34 summary: Introduction The communication engineering major mainly trains the product implementation, operation and maintenance departments for intelligent communication equipment, network communication enterprises and other various enterprises and institutions, and trains high-level technical and skilled talents engaged in the testing and development of mobile communication products and intelligent communication equipment, pre-sales and after-sales engineers, and network operation and maintenance. Based on the background of Huawei's school enterprise cooperation, guided by the output of students' learning achievements and ability development, this paper studies the significance and cooperation methods of school enterprise cooperation in this course, which can better serve the curriculum system of communication engineering and lay a better foundation for training application-oriented talents. keywords: enterprise; huawei; network; school; teaching; technology cache: fcis-1885.pdf plain text: fcis-1885.txt item: #271 of 872 id: fcis-1886 author: Wang, Xichen; Liang, Tijian; Wang, Yangguang; Li, Longfei; Zhou, Zejiong title: Research on Employment Effect of Digital Economy date: 2022 words: 4445 flesch: 35 summary: Only by complying with the development model, actively improving the industry regulations and systems on the development of digital science and technology in various platforms, ensuring the standardization and popularization of the employment model of digital economy development, and realizing the popularization of digital economy employment for all, can China's digital economy develop to the forefront of the world. In addition to Beijing, Shanghai and Zhejiang, three provinces and cities with rapid digital economy development, the monthly salary of digital economy staff in other provinces and cities ranked in the top ten in digital economy development is generally within the range of 5000-8000, while the monthly salary of staff in other cities is less than 5000. keywords: china; development; digital; economy; economy development; employment; impact; number cache: fcis-1886.pdf plain text: fcis-1886.txt item: #272 of 872 id: fcis-1906 author: Zheng, Yingya title: Application of Distributed wMPS System in AGV Automatic Navigation date: 2022 words: 2959 flesch: 50 summary: The results show that the comparison error between the constructed measurement field and the measurement results of the tracker is controlled below 0.2mm, 4 which can effectively meet the accuracy requirements of AGV vehicle automatic navigation. In order to improve the navigation accuracy of AGV vehicles, based on the workspace measuring and positioning system (wMPS), this paper proposes to use upright and top mounted transmitter stations to build precision coordinate measuring fields, and analyzes the construction process and layout optimization principle of precision measuring fields in detail, Finally, the measurement accuracy of the coordinate field is illustrated through experiments. keywords: agv; area; measurement; navigation; station; system; wmps cache: fcis-1906.pdf plain text: fcis-1906.txt item: #273 of 872 id: fcis-1907 author: Yu, Yongqiang title: Review of epileptic EEG feature extraction methods date: 2022 words: 1906 flesch: 43 summary: In this paper, several methods of epilepsy EEG feature extraction are summarized from four aspects: time domain analysis, frequency domain analysis, time frequency analysis and nonlinear dynamics, and each method is systematically summarized. The advantage of time domain analysis is that the physical meaning is clear, with strong intuitiveness, simple and fast calculation; The disadvantage is that time domain analysis is not sufficient to fully reflect the information contained in EEG signals. keywords: analysis; domain; eeg; frequency; signal; time cache: fcis-1907.pdf plain text: fcis-1907.txt item: #274 of 872 id: fcis-19452 author: Hu, Jiaxin; Zhang, Xinchen; Xiao, Shuangyue; Fan, Linli; Liu, Li; Li, Tao; Huang, Miaoqi title: Correlative Analysis and Prediction of Physical Education Data Via Machine Learning: A Case Study on Grade Evaluation Method in University date: 2024 words: 5519 flesch: 53 summary: With the continuous in-depth study of data, various methods of processing and analyzing data have been developed[3]; by inviting student participation data and past performance data, classification and regression tasks are performed, and then artificial neural networks are used to obtain the highest overall Accuracy, providing comprehensive analysis and comparison, is the latest supervised machine learning technology used to solve the task of predicting student test scores, that is, discovering students in a high-risk dropout state, and predicting their future results, such as final exam results[4]. This article analyzes the details of physical fitness test results and the relationship with the comprehensive score. keywords: analysis; data; fitness; layer; model; network; neural; physical; principal; results; score; students; test cache: fcis-19452.pdf plain text: fcis-19452.txt item: #275 of 872 id: fcis-19455 author: Xu, Yuhang; Chen, Peng title: Analysis on the Application of Image Processing in UAV and Autopilot date: 2024 words: 2766 flesch: 42 summary: Image processing technology is an important branch of digital image processing, which aims to obtain the information contained in the image and make corresponding decisions through a series of operations such as image acquisition, processing, analysis and recognition [4]. For UAV, in agricultural plant protection and natural disaster monitoring, the rapid evaluation and identification of farmland growth status and disaster situation can be realized through image processing technology, which provides important support for crop production and rescue work. keywords: driving; image; image processing; processing; technology; uav cache: fcis-19455.pdf plain text: fcis-19455.txt item: #276 of 872 id: fcis-19513 author: Zhou, Shouliang; Wang, Zixuan title: Transformation of Financial Accounting to Management Accounting in the Era of Artificial Intelligence date: 2024 words: 4180 flesch: 20 summary: Financial personnel need to consciously abandon some low value-added work, cultivate individual ability to solve management conflicts, and obtain more favorable information as much as possible and integrate it to provide decision support for financial management. Management accounting personnel need to master rich and systematic financial theoretical knowledge, timely understand customer needs, pay attention to the dynamic changes in the market, through the combination of management accounting, can master the specific trend of management policies, help to use relevant research results to assist the company to implement performance assessment. keywords: accounting; data; enterprises; information; intelligence; management; management accounting; personnel cache: fcis-19513.pdf plain text: fcis-19513.txt item: #277 of 872 id: fcis-19514 author: Cao, Yang; Zhang, Meina; Jia, Simiao; Shang, Yaqin; Wang, Xianjun title: Study of Road-based Versus Pattern-based Game Strategies in Connect6 date: 2024 words: 2682 flesch: 63 summary: Abstract: Computer game is an important branch in the field of artificial intelligence research nowadays, and the in-depth study of computer game can not only promote the development of game theory, but also contribute to the development of artificial intelligence. In the field of computer gaming, chess computer games are flourishing, including Rokko, Tibetan Kyuqi, Go, Backgammon, Xiangqi, Surakarta, and so on. keywords: board; chess; game; road; search; strategy cache: fcis-19514.pdf plain text: fcis-19514.txt item: #278 of 872 id: fcis-19515 author: Fan, Jiajun; Du, Zhibo title: Side-Channel Attacks Against the FESH Algorithm date: 2024 words: 4879 flesch: 52 summary: CPA attack results against FESH algorithm stage 2k 5k 1w Top-1 Top-4 Top-1 Top-4 Top-1 Top-4 sboxin 1.0 1.0 1.0 1.0 1.0 1.0 sboxout 0.25 0.5 0.188 0.75 0.188 0.75 mixword 0.0 0.06 0.0 0.0 0.0 0.06 By obtaining the success rates for the first four ranks, it can be concluded that if a random plaintext is used for side- channel attacks on the FESH algorithm, the key value can be obtained through a CPA attack on the leakage point of the S- box input. FESH algorithm version and number of rounds Algorithm version Plaintext Block Length Key Block Length Number of Rounds FESH-128-* 128 bit 128/192/256 bit 16/20/20 FESH-256-* 256 bit 256/384/512 bit 24/28/28 The encryption process of the FESH algorithm is based on word operations. keywords: algorithm; analysis; attack; channel; correlation; dataset; fesh; key; leakage; model; power; results; transnet cache: fcis-19515.pdf plain text: fcis-19515.txt item: #279 of 872 id: fcis-19516 author: Yan, Fangxu; Wang, Jianhui title: Research on Sentiment Analysis of Micro-blog based on Attention-BiLSTM date: 2024 words: 1743 flesch: 54 summary: In order to explore the value and sentiment contained in micro-blog comment texts, and solve the problem of semantic loss and over-reliance on manual work in traditional text sentiment analysis, this paper proposes a deep learning model based on Attention-BiLSTM. The result proves that the model gains much better accuracy, flexibility and feasibility in the field of text sentiment classification. keywords: attention; bilstm; data; model; sentiment; text cache: fcis-19516.pdf plain text: fcis-19516.txt item: #280 of 872 id: fcis-19517 author: Hou, Bingxu; Li, Meihui; Guan, Jiayu; Bai, Junming; Liu, Qian title: Research on Intelligent Airbag Technology for Snowboarding Suits based on Arduino and Embedded Systems date: 2024 words: 2331 flesch: 37 summary: This study aims to explore the application of embedded systems and Arduino in improving the safety of snowboarding suits. Introduction This research develops an intelligent airbag device for snowboarding suits, using embedded systems and Arduino to enhance skier safety. keywords: airbag; arduino; design; safety; skiing; system; time cache: fcis-19517.pdf plain text: fcis-19517.txt item: #281 of 872 id: fcis-19575 author: Zhang, Yuanyuan; Wang, Liqiang title: Review of Metal-Resistant Structures for Radio Frequency Identification Tag Antennas date: 2024 words: 3672 flesch: 41 summary: Consequently, there is a pressing need for the development of RFID tag antennas endowed with metal-resistant properties. In practical settings, RFID tag antennas are frequently positioned in metallic environments, where metals can reflect or scatter electromagnetic waves, resulting in several adverse effects when in proximity to metal objects: (1) Electromagnetic waves encountering metal reflections precipitate a sharp decline in the antenna's radiation resistance, leading to impedance mismatch. keywords: antenna; design; frequency; metal; propagation; radio; resistance; rfid; structure; tag; uhf cache: fcis-19575.pdf plain text: fcis-19575.txt item: #282 of 872 id: fcis-19577 author: Li, Jinxiang; Liu, Huateng; Nie, Gonghao title: Intelligent Monitoring System for the Elderly based on Posture Recognition date: 2024 words: 3148 flesch: 59 summary: Web Server Design In this paper, the Web interface server with multi- architecture mode is chosen as the feedback component of the system, and the server and the client use WebSocket to establish connection and transmit data, the image transmission achieved by WebSocket has real-time, which is suitable for the scenarios that require real-time monitoring or transmission of image data. 3.3. Design and implementation of fall detection system for elderly patients. keywords: algorithm; data; detection; image; model; module; sensor; state; system; time cache: fcis-19577.pdf plain text: fcis-19577.txt item: #283 of 872 id: fcis-19688 author: Zhang, Jingbo; Xiao, Lingxi; Zhang, Yuwei; Lai, Jiatao; Yang, Yutian title: Optimization and Performance Evaluation of Deep Learning Algorithm in Medical Image Processing date: 2024 words: 3612 flesch: 48 summary: In medical image processing, many different types of medical image data, such as MRI, CT and X-ray, are often involved. 1. Introduction Medical image processing is one of the important branches in the medical field, which covers many aspects such as extracting information from medical image data, diagnosing diseases and assisting doctors in decision-making. keywords: data; image; image processing; learning; model; performance; processing; rate; training cache: fcis-19688.pdf plain text: fcis-19688.txt item: #284 of 872 id: fcis-19695 author: Gong, Yulu; Qiu, Hongjie; Liu, Xiaoyi; Yang, Yutian; Zhu, Mengran title: Research and Application of Deep Learning in Medical Image Reconstruction and Enhancement date: 2024 words: 3550 flesch: 39 summary: In medical image reconstruction, Autoencoder can be used to process medical images with low resolution and large noise interference, thus improving the quality and clarity of the images. Use the public radiology image data set, LIDC-IDRI (lung CT image data set) and IXI data set (magnetic resonance image data set) to ensure that the data set contains medical image data of different cases and different diseases. 3.2. keywords: autoencoder; data; enhancement; image; learning; model; processing; reconstruction cache: fcis-19695.pdf plain text: fcis-19695.txt item: #285 of 872 id: fcis-1973 author: He, Jingyuan; Yang, Bailong title: Fine-grained Image Recognition Method using Discriminative Region-based Data Augmentation date: 2022 words: 4045 flesch: 46 summary: The random cropping data augmentation method proposed by Krizhevsky et al. can effectively improve the accuracy, and then a series of image translation data augmentation methods appear. Drawing on the idea of data augmentation algorithm based on attention mechanism, literature proposes a multi-sample data augmentation algorithm based on spatial and channel attention for fine-grained image classification, which can effectively distinguish image features while making the training data more diverse, and further solve the problem of overfitting of network models. keywords: augmentation; data; discriminative; feature; image; image recognition; map; method; model; recognition; region cache: fcis-1973.pdf plain text: fcis-1973.txt item: #286 of 872 id: fcis-1975 author: Lu, Zhigang; Hu, Jian; Niu, Tao; Zuo, Yonggang title: Smart home design based on Alibaba Cloud date: 2022 words: 2864 flesch: 53 summary: The application of Internet of Things technology in smart home control system aims to connect electrical appliances and living facilities in the home together to achieve video surveillance, intelligent anti-theft, intelligent lighting, intelligent electrical control, intelligent door and window control, intelligent audio-visual system control and other functions .Users can achieve remote real- time control of lights, curtains and appliances at home through computers, tablets and smart phones. Temperature and humidity detection and temperature control function keywords: control; data; detection; home; humidity; sensor; signal; system; temperature cache: fcis-1975.pdf plain text: fcis-1975.txt item: #287 of 872 id: fcis-19793 author: Wang, Haishan; Wang, Binbin; Wang, Siyu title: Design and Implementation of a Primary Healthcare Cloud Platform date: 2024 words: 5373 flesch: 28 summary: Spring Security offers comprehensive security functions, including authentication and authorization, and can effectively withstand common security threats such as CSRF and XSS, ensuring the security of medical information system data. Most medical information systems are designed to meet the needs of large hospitals, and their complexity and high costs often exceed the capacity of primary healthcare institutions. keywords: cloud; data; design; healthcare; information; institutions; management; patient; platform; project; security; service; system; testing; user cache: fcis-19793.pdf plain text: fcis-19793.txt item: #288 of 872 id: fcis-2017 author: Dai, Xu; Li, Man; Ma, Heji title: Weight-bearing cross-country running influences on the knee articular cartilage -a study using T2 MRI and muscle monitoring date: 2022 words: 2869 flesch: 49 summary: [8] H.G. Potter, B.R. Black, L.R. Chong, “New techniques in articular cartilage imaging,” Clin Sports Med, vol.28, pp. In this way,T2 relaxation time has potential to serve as a characterized imaging parameter that can reflect the knee articular cartilage biochemical conponents and health status upon appropriate quantification. keywords: cartilage; imaging; knee; loading; mri; muscle; relaxation; running; time cache: fcis-2017.pdf plain text: fcis-2017.txt item: #289 of 872 id: fcis-2020 author: Dao, Juwei title: A Survey of Knowledge Tracking Based on Deep Learning date: 2022 words: 3240 flesch: 43 summary: The scientific knowledge map of keyword co-occurrence in knowledge tracking research based on deep learning in China is shown in Figure 2, with 148 nodes and 299 links. Research development stage and future research space In order to analyze the academic frontier information of knowledge tracking research based on deep learning in China, the emergent word map of artificial intelligence applied to teaching management and evaluation is derived through citespace software. keywords: analysis; data; education; knowledge; learning; model; research; tracking cache: fcis-2020.pdf plain text: fcis-2020.txt item: #290 of 872 id: fcis-2022 author: Li, Jinfeng title: Low-light image enhancement with contrast regularization date: 2022 words: 2507 flesch: 56 summary: Conclusion Aiming at the problem of low light enhancement, this paper proposes a new multi-scale low-light image enhancement network with regularized contrast. [3] Guo, X., Li, Y. and Ling, H., “Lime: Low-light image enhancement via illumination map estimation,” IEEE Transactions on image processing, vol. 26, no. 2, pp. keywords: enhancement; ieee; image; light; methods; network; processing; transactions cache: fcis-2022.pdf plain text: fcis-2022.txt item: #291 of 872 id: fcis-20314 author: Xu, Haihui; Ge, Zhiyuan; Ao, Wenjie title: Research on Climate Change Prediction based on ARIMA Model and its Impact on Insurance Industry Decision-Making date: 2024 words: 2366 flesch: 40 summary: Different from traditional insurance, weather insurance has the advantage of quick realization of compensation amount. The adjustment of different industries to weather changes also reflects their demand for weather insurance on the other hand. keywords: humidity; insurance; model; new; weather; york cache: fcis-20314.pdf plain text: fcis-20314.txt item: #292 of 872 id: fcis-20320 author: Ren, Cheng; Hou, Shouming title: A Hybrid Deep Learning Approach for Lung Nodule Classification date: 2024 words: 5574 flesch: 49 summary: [10] P. Wu, X. Sun, Z. Zhao, H. Wang, S. Pan, B. Schuller, Classification of lung nodules based on deep residual networks and migration learning, Computational intelligence and neuroscience, 2020 (2020). For pulmonary nodule classification, Li et al. keywords: classification; function; layers; learning; lung; malignant; model; network; nodules; performance; resnet; results; vgg cache: fcis-20320.pdf plain text: fcis-20320.txt item: #293 of 872 id: fcis-20325 author: Wang , Siyu; Wang, Haishan title: Digital Transformation in Real Estate Services: Development and Implementation of the Housing Selection Platform date: 2024 words: 5373 flesch: 28 summary: For housing transaction platforms, these advancements will drive the entire industry towards greater efficiency, intelligence, and user-centricity. In this era, real estate platforms have become more than just aggregators of information; they have transformed into intermediaries and service providers for housing rental and transactions. keywords: data; development; end; experience; housing; housing selection; performance; platform; security; selection; selection platform; service; system; user cache: fcis-20325.pdf plain text: fcis-20325.txt item: #294 of 872 id: fcis-20335 author: Chen, Xiaoyi title: The Application of Artificial Intelligence in Healthcare date: 2024 words: 2606 flesch: 36 summary: Only by actively responding to the ethical challenges brought by medical artificial intelligence can medical artificial intelligence technology develop in a direction conducive to human health Medical artificial intelligence not only brings us more high-quality and efficient medical services, but also brings a series of ethical risks and challenges. keywords: care; doctors; health; intelligence; medical; patients; technology cache: fcis-20335.pdf plain text: fcis-20335.txt item: #295 of 872 id: fcis-20342 author: Wang, Rending; Ma, Dongmei title: Improved Multi-attention Neural Networks for Image Emotion Regression and the Initial Introduction of CAPS date: 2024 words: 9595 flesch: 47 summary: In the current research in the field of image emotion, the mainstream datasets are all based on the collection of foreign social platforms and picture websites, and the annotators are also more internationalized. In the early days, among them, IAPS was the most commonly used dataset for image emotion stimuli, in addition to its subset IAPSa keywords: attention; caps; chinese; dataset; emotion; iaps; image; loss; model; module; paper; pdanet; results; sentiment; simam; test; training cache: fcis-20342.pdf plain text: fcis-20342.txt item: #296 of 872 id: fcis-20343 author: Tang, Lin; Zhou, Shunyong; Wang, Xinjie title: A Lightweight Object Detection Network for UAV Aerial Images date: 2024 words: 6255 flesch: 51 summary: Abstract: In order to solve the problems of poor detection algorithms, high network model complexity, and difficult deployment of algorithms in the field of aerial image target detection. And achieved good results and verify the applicability of the proposed algorithm; Zeng[30] et al. improved the YOLOv7 algorithm by removing the second down-sampling layer and the deep detection head, introducing the DpSPPF module and adding the NWD measurement method to the indicators of positive and negative sample allocation, and proposed a real- time small target detection algorithm YOLOv7-UAV.Aiming at the current challenges in the field of UAV target detection, Li[31]et al. proposed an aerial image detection model with excellent performance based on YOLOv8 algorithm. keywords: algorithm; box; detection; detection algorithm; detection network; feature; images; loss; model; network; object; paper; target detection; uav; yolov7 cache: fcis-20343.pdf plain text: fcis-20343.txt item: #297 of 872 id: fcis-20387 author: Wan, Ruihao title: Research on Air Quality Prediction Based on Neural Networks date: 2024 words: 3180 flesch: 42 summary: This paper mainly introduces the current research status of air quality prediction. Current Status of Research on Air Quality Prediction With the rapid development of neural networks, more and more researchers use neural network-based models in the field of air quality prediction. keywords: air; algorithm; model; network; neural; prediction; quality cache: fcis-20387.pdf plain text: fcis-20387.txt item: #298 of 872 id: fcis-2051 author: Yao, Xuefei title: Research on the Innovative Development of University Library Subject Services Under the Background of Big Data date: 2022 words: 1918 flesch: 30 summary: Talents, in the process of recruiting talents, we can use competitive assessment methods, combined with the background of subject services, and examine in detail the subject foundation, language communication ability, foreign language level and computer skill level of talents, so as to play the role of subject service, and can also face social recruitment. For example, let subject service librarians participate in front-line scientific research, investigate scientific research content and scientific research trends, establish strategic cooperative relations with scientific research personnel, continuously optimize the content of subject services, and identify the direction of content construction, such as conducting research in university scientific research teams. keywords: library; services; subject; university cache: fcis-2051.pdf plain text: fcis-2051.txt item: #299 of 872 id: fcis-2052 author: Lu, Ronghua title: Design of Bad Information Filtering System for Web Pages date: 2022 words: 2018 flesch: 46 summary: Keywords: Web page information filtering; Network data processing; Text data processing; Chinese word segmentation technology; Text representation technology; Adaptive processing. This method is accurate and fast, and can ensure the real-time performance of web page filtering. keywords: filtering; information; system; user; web cache: fcis-2052.pdf plain text: fcis-2052.txt item: #300 of 872 id: fcis-20527 author: Song, Han; Gan, Luying; Sha, Yue title: Intelligent Service of College Library based on the Demand of Compound Talents Training Path Analysis date: 2024 words: 4255 flesch: 25 summary: Due to the continuous development and progress of network information, the time and space of library service is also undergoing great changes, and the network information service of the library has become an important part of the knowledge service process. Innovative Services for Specialized Resources Characteristic resources is the root of library services in the network environment, characteristic resources are different from the library's traditional types of literature, in the content of its unique collection, college libraries should fully explore the characteristic resources and characteristic services, the school's characteristic professions and special subjects, digitize the collection and build a characteristic resource database, use the library's rich knowledge resources to carry out the characteristic knowledge services. keywords: data; development; information; knowledge; libraries; library; resources; service; students; talents cache: fcis-20527.pdf plain text: fcis-20527.txt item: #301 of 872 id: fcis-2053 author: Ren, Qiong; Chang, Junming title: Research on the Fusion Trend of Artificial Intelligence and VR Based on Data Mining date: 2022 words: 2635 flesch: 36 summary: Considering the higher concealment of VR applications, criminals are more likely to use VR devices to achieve the purpose of series, incitement, or reactionary propaganda. If users want to obtain VR applications, they can only search through keywords, which is not conducive to promoting and popularizing VR applications. keywords: application; data; development; intelligence; mining; technology cache: fcis-2053.pdf plain text: fcis-2053.txt item: #302 of 872 id: fcis-2054 author: Guo, Yixuan title: Demonstration of Neutral Grounding Mode of New 10kV Distribution System in Nuclear Power Station date: 2022 words: 2433 flesch: 52 summary: The neutral ground mode through medium resistance and small resistance is suitable for the urban distribution network and plant power system, which are mainly cable lines, are not prone to instantaneous single-phase ground fault and the system capacitance current is relatively large. Keywords: Power distribution system; Neutral grounding; Nuclear power plant. keywords: grounding; plant; power; resistance; supply; system cache: fcis-2054.pdf plain text: fcis-2054.txt item: #303 of 872 id: fcis-2068 author: Gao, Xingbang; Li, Jiaojiao; Liu, Ruiyuan; Zhang, Shuai; Ma, Pengcheng title: Research on Vehicle Longitudinal Control Method Based on Model Predictive Control date: 2022 words: 4652 flesch: 51 summary: As one of the three major technical fields of autonomous driving, vehicle motion control can complete the lateral control, longitudinal control and lateral longitudinal coupling control of autonomous vehicles according to the target planning path and speed. Zhang et al. used double PID controller to control the speed and position error of vehicle longitudinal motion. keywords: acceleration; braking; control; driving; model; motion; speed; vehicle; vehicle speed cache: fcis-2068.pdf plain text: fcis-2068.txt item: #304 of 872 id: fcis-2069 author: Zhai, Junhao; Shi, Yunqiu title: Design of Labor Education System in Primary and Secondary Schools Based on Big Data date: 2022 words: 5098 flesch: 29 summary: Student Parents Management Unit The end student management module is used to add, delete, check and manage registered users; Parent-end student schedule module, which is used to manage the class schedules of related students and the individual schedules generated by 50 users' self-registration for students, check the details of the courses through the schedules, and complete the synchronization of online learning links related to the courses and offline practice information; The pre-class preview module of labor education is used for online preview of the pre-class audio and video content of students who have participated in labor education courses; The labor education pre-class exercise module is used to submit and view the task exercises of the labor education courses that students have participated in; In the course of labor education, the trip punching module, under which the teacher updates the students' trip status in real time, and the parents check the progress of the students' trip status in real time; The task module in the labor course, under which the teacher updates the students' task completion status in real time, and the parents check the progress of the students' task completion status in real time; The dynamic live broadcast module in the labor education course updates the pictures, audio and video materials of current labor education in real time, and parents can check the progress of students' trip status in real time; After-class homework module of labor education course, which submits and views after-class homework for students who have participated in labor education course after the course is over; The file module of comprehensive evaluation of students' labor education, after students have studied all kinds of labor education courses in the education system, the relevant data are recorded in the file of comprehensive evaluation of students' labor education; The student album module, taking students and courses as dimensions, automatically classifies the pictures and videos generated in the dynamic process of courses related to students into the student album; The student certificate module is used to store the course certificates that students have obtained; The personal data module is used to summarize and display registered users and students, registration information, photo albums, archives and personal information related to registered users. Base/organization management The curriculum management module of the base/institution is used to publish the labor education curriculum information and curriculum plan of the institution, and perform management operations such as adding, deleting, checking, loading and unloading products and submitting them for review; The student management module of the base/institution is used to manage the students enrolled in the labor education courses of the institution, and the management contents specifically include: basic information of students, information of associated users, school information, information of participating in labor education, and labor education files; The registration management module of base/institution: counts and views the online transaction registration generated by the labor education courses released by this institution; Base/institution data management module, which is used to view and manage the data related to labor courses released by this institution; The registration management module of base/institution manages the registration data related to labor education courses issued by this institution. keywords: courses; data; education; information; labor education; management; module; school; students; unit cache: fcis-2069.pdf plain text: fcis-2069.txt item: #305 of 872 id: fcis-2071 author: Li, Peiye title: Classification of black tea leaf water content based on hyperspectral imaging date: 2022 words: 2486 flesch: 50 summary: Therefore, it is feasible to use hyperspectral imaging technology and related classification algorithms to nondestructively identify and classify the water content of black tea leaves during the tail-withering process. Experimental materials Hyperspectral imaging-based water content classification study of black tea leaves Ying Hong IX was collected at Ying Hong Farmer Eco-Farm, Ying Hong Town, Yingde City, Guangdong, China. keywords: algorithm; classification; content; hyperspectral; image; leaves; tea; water cache: fcis-2071.pdf plain text: fcis-2071.txt item: #306 of 872 id: fcis-20710 author: Ye, Ling title: The Feasibility Study of Artificial Intelligence ChatGPT in Translation Field date: 2024 words: 5287 flesch: 34 summary: Promote the Feasibility of High-quality Translation We are in the midst of a revolution led by AI technology, especially in the field of translation technology, and the rapid development of ChatGPT technology is changing the way we work and learn. The Application Dilemma of ChatGPT in the Field of Translation In a revolution led by artificial intelligence technology, especially in the field of translation technology, the rapid development of ChatGPT technology is changing the way we work and learn. keywords: artificial; chatgpt; data; ethics; intelligence; language; students; technology; text; translation; use cache: fcis-20710.pdf plain text: fcis-20710.txt item: #307 of 872 id: fcis-20715 author: Ouyang, Zijing; Xu, Sheng; Su, Chengyue title: Tracking Control Based on Model Predictive and Adaptive Neural Network Sliding Mode of Tiltrotor UAV date: 2024 words: 6368 flesch: 61 summary: Therefore, the control law for the kinematic controller of tiltrotor UAV can be designed as: T T T T T T TT 1 2f ˆv v b ( ) ( ) /T in se K s K sgn s W h k x s                   (25) In this matrix, the forms of matrices G T R and G T W are as follows: T T T T T T T T T T T T G T T T T T T T T T T T T T T T T T T cos cos cos sin sin cos sin sin sin cos cos sin R cos sin cos cos sin sin sin cos cos sin cos sin sin cos sin cos cos                keywords: control; controller; k k; path; t t; tiltrotor; tracking; trajectory; uav;  ;  ;   cache: fcis-20715.pdf plain text: fcis-20715.txt item: #308 of 872 id: fcis-2072 author: Liu, Bohua; Gou, Mengjiao; Sun, Xiaomao; Du, Hengyi title: Application of Artificial intelligence in Computational fluid dynamics date: 2022 words: 3004 flesch: 41 summary: Conclusion and Prospect The application of artificial intelligence in computational fluid dynamics is various, involving geometric parameter model, mesh division, turbulence model calculation and scientific visualization of flow field, etc. As the geometric shape and flow field become more and more complex, the modeling and mesh generation, as an important part of the whole calculation and analysis process, are more difficult to achieve by manual operation, which requires a lot of time and manpower. keywords: cfd; dynamics; flow; fluid; grid; model; process; simulation; technology cache: fcis-2072.pdf plain text: fcis-2072.txt item: #309 of 872 id: fcis-20720 author: Wang, Junliang title: Research on Development of Generative Artificial Intelligence date: 2024 words: 3410 flesch: 37 summary: This study provides a relatively systematic introduction to machine learning. Firstly, it gives an overview of the historical development of machine learning, and then focuses on the analysis of classical algorithms in machine learning. keywords: algorithm; computer; data; development; intelligence; learning; machine; technology cache: fcis-20720.pdf plain text: fcis-20720.txt item: #310 of 872 id: fcis-20728 author: Shi, Mo; Xu , Xiaoyan; Choi, Yeol title: Gaussian Analysis of the Elevator Traffic under the Typical Office Building date: 2024 words: 6253 flesch: 35 summary: By examining the performance of LS-SVMs in predicting elevator traffic and comparing it with actual monitored data, this study underscores the effectiveness and rationality of using LS-SVMs as a predictive tool in elevator traffic analysis. Discussion of Gaussian Fitting Results Figure 3 serves as a visual representation of the Gaussian fitting curves generated through MATLAB, offering insights into the temporal distribution of elevator traffic peaks observed over the course of a full daytime cycle. keywords: analysis; data; dynamics; elevator; elevator traffic; fitting; gaussian; passenger; patterns; rush; traffic cache: fcis-20728.pdf plain text: fcis-20728.txt item: #311 of 872 id: fcis-21087 author: Yu, Zhongyu; Xu, Xin; Liu, Hao; Wu, Zeju title: Analysis of Dispersibility and Mechanical Properties of Lignin Modified Dispersive Soil date: 2024 words: 3780 flesch: 54 summary: Through microscopic analysis of lignin improved soil samples, it can be concluded that lignin fibers play a stereograin-like bridging role in soil, which promotes the formation of larger aggregates, weakens the dispersion of single soil particles, and thus reduces the dispersion of soil mass and improves the strength of soil mass. Wang et al.[7] conducted a dry and wet cycle test on the improved soil with 3% lignin content, and compared it with quicklime improved soil with the same properties such as pH, unconfined compressive strength, appearance and volume stability, and 84 found that the overall stability of lignin improved soil was superior to that of quicklime improved soil. keywords: content; curing; lignin; lignin content; soil; strength; test cache: fcis-21087.pdf plain text: fcis-21087.txt item: #312 of 872 id: fcis-21091 author: Chang, Yanping; Li, Qibin; Zhang, Jianan title: Application Analysis of Security Situational Awareness System in Qinghai Provincial Meteorological Network date: 2024 words: 2472 flesch: 20 summary: Therefore, the deployment and application of situational awareness system is very necessary and effective for Qinghai meteorological network security. This issue is also the core issue of meteorological network security, the current Qinghai meteorological network security equipment linkage structure, personal terminal leakage of data behavior will be monitored by the terminal management module, the server and the virtual machine data leakage through the firewall as well as behavioral management module for control, both play an effective role in preventing data leakage from the root cause of the incident. keywords: awareness; data; meteorological; network; qinghai; security; system cache: fcis-21091.pdf plain text: fcis-21091.txt item: #313 of 872 id: fcis-21096 author: Liu, Yixuan title: Design and Implementation of a Student Attendance Management System based on Springboot and Vue Technology date: 2024 words: 2800 flesch: 34 summary: Class Management Administrator can log in and enter the system to view the home page, personal center, student management, teacher management, class information management and other functions. The system adopts a modularized design, covering functional modules such as user management, student management, teacher management, class and course management, attendance record, leave management, statistical report and system settings. keywords: attendance; class; data; information; kaoqinxinxientity; management; student; system cache: fcis-21096.pdf plain text: fcis-21096.txt item: #314 of 872 id: fcis-2110 author: Gou, Mengjiao; Liu, Bohua; Sun, Xiaomao; Ma, Yuli title: Computational fluid dynamics grid technology development date: 2022 words: 2918 flesch: 46 summary: Steger et al. mainly used the dot product result of the normal vector of grid surface and the relative position vector of grid points to judge the relationship between grid points and surface. The adjacency between unstructured grid points is disordered and irregular, and each grid point can have different number of adjacency grids. keywords: cfd; grid; hole; mesh; method; point; surface; technology cache: fcis-2110.pdf plain text: fcis-2110.txt item: #315 of 872 id: fcis-21102 author: Huang, Chao; Yang, Weiping title: Ethereum Eclipse Attack Detection based on BG-XGBoost date: 2024 words: 5385 flesch: 45 summary: The principle of Ethereum Eclipse attack is shown in the figure 1. It further enhances the model performance on binary classification problems and achieves efficient identification of Eclipse attack traffic and normal traffic. keywords: accuracy; attack; blockchain; data; detection; eclipse; ethereum; model; network; security; traffic; xgboost cache: fcis-21102.pdf plain text: fcis-21102.txt item: #316 of 872 id: fcis-21104 author: Liu, Yingfang; Dai, Wanchang; Wang, Yuli title: The Development of the Integrated Media Teaching Materials of Linux Network Operating System with "Paper-based Teaching Materials + Electronic Loose-leaf Pages" date: 2024 words: 2202 flesch: 36 summary: This kind of teaching materials can provide personalized learning plans according to the characteristics and needs of 105 students. Research on improving digital experiments based on the learning activity suggestions of the curriculum standards - from the perspective of the deep integration of hand-held technology and the secondary development of teaching materials [J]. keywords: leaf; materials; pages; system; teaching cache: fcis-21104.pdf plain text: fcis-21104.txt item: #317 of 872 id: fcis-21105 author: Su, Xiran title: Research on Application of Multi-modal Large Model in Robot Control date: 2024 words: 3279 flesch: 44 summary: China Abstract: This study discusses the application of multi-modal large model in robot control. Then, aiming at the specific application scenarios in smart home environment, this paper designs a series of experiments to evaluate the performance of multi-modal large model in path planning, task effect and generalization ability. keywords: application; control; environment; modal; robot; task cache: fcis-21105.pdf plain text: fcis-21105.txt item: #318 of 872 id: fcis-21106 author: Li, Chen; Huang, Zengyi title: Using Artificial Intelligence to Refine the Implementation Trajectory of Digital Image Processing Technology date: 2024 words: 3378 flesch: 22 summary: In the field of security and surveillance, image processing technologies are utilized for facial recognition, object detection, and anomaly detection, enhancing public safety and crime prevention measures. Advantages of Image Techniques The process of digital image processing technology involves converting image signals into digital signals, a task performed by computers, hence also referred to as computer image processing technology. keywords: image; image processing; intelligence; learning; processing; restoration; segmentation; techniques; technology cache: fcis-21106.pdf plain text: fcis-21106.txt item: #319 of 872 id: fcis-21109 author: Chang, Yanping; Li, Qibin; Zhang, Jianan title: Research on Atmospheric Attenuation Compensation Technology of High-Frequency Band Microwave in Long-Distance Transmission date: 2024 words: 1686 flesch: 32 summary: However, high-frequency band microwaves are seriously affected by atmospheric attenuation during transmission, especially at long distances, and this attenuation significantly reduces the signal strength and quality. Therefore, the study of accurate modeling of atmospheric attenuation as well as effective compensation techniques is crucial for improving the performance of long-distance transmission of high-frequency band microwaves. keywords: atmospheric; attenuation; microwave; signal; transmission cache: fcis-21109.pdf plain text: fcis-21109.txt item: #320 of 872 id: fcis-21111 author: Zhou, Zhenjing title: Building a Smart Ecological Education in the AI Era date: 2024 words: 2015 flesch: 28 summary: The application of artificial intelligence technology in the field of education has promoted the high-quality development of education in six aspects: student learning, teacher research, school management, home-school co-education, and teaching evaluation, further advancing the transformation of the educational ecosystem. 2.1. In many predicted areas, education has seen an efficiency improvement of up to 82%, impacting not only teaching practices but also student learning. keywords: development; education; intelligence; learning; teaching; technology cache: fcis-21111.pdf plain text: fcis-21111.txt item: #321 of 872 id: fcis-21118 author: Mei, Chongbin; Wen, Yucheng title: Subway Tunnel Crack Identification based on YOLOv5 date: 2024 words: 4642 flesch: 54 summary: It is difficult for traditional methods to meet the current requirements for tunnel crack detection. In recent years, with the rapid development of big data and artificial intelligence, deep neural networks, as a discriminative structure algorithm, have excellent performance in image classification and target detection, and are suitable for scenarios with large amounts of data such as tunnel crack detection. keywords: accuracy; algorithm; crack; detection; feature; figure; image; model; module; network; tunnel; yolo cache: fcis-21118.pdf plain text: fcis-21118.txt item: #322 of 872 id: fcis-21119 author: Zhang, Jian; Zhang, Liguo; Zhang, Guanghui; Yu, Yang title: From Theory to Practice: Project-Based Learning in Computer Science Education date: 2024 words: 2205 flesch: 32 summary: This development should encompass training in PBL pedagogy, instructional techniques, and team management to enhance teachers' abilities to guide and assess student projects effectively. Enhanced collaboration Instructional Guidance Regular guidance and feedback on PBL practices. keywords: education; learning; pbl; programming; project; research; students cache: fcis-21119.pdf plain text: fcis-21119.txt item: #323 of 872 id: fcis-21120 author: Liu, Junli; Lu, Hui; Cui, Guanhui; An, Xibin title: Research on the Application of CBR Technology in Intelligent Process Design System date: 2024 words: 3077 flesch: 49 summary: Improved algorithm for case feature weight based on sensitivity analysis [J].Computer Science, 2010, 37(5):194-196. Taking the roller shaft of belt conveyor as an example, the description and expression of different attribute information in shaft process cases are given, and a global similarity calculation model is established. keywords: attribute; calculation; case; design; features; method; process; similarity cache: fcis-21120.pdf plain text: fcis-21120.txt item: #324 of 872 id: fcis-21121 author: Li, Chen; Hou, Zhesheng; Wang, Yu; Zhang, Xin title: Research and Design of STM32 and Qt based Medical Smart Cockpit Convenient Medical Care System date: 2024 words: 1745 flesch: 51 summary: In this paper, we design a convenient medical system for medical intelligent cockpit, the main function is to transfer the corresponding data collected by sensors to the microcontroller and process them, in order to realise the function of user self-help to choose medical treatment and convenient medical treatment. Functional module diagram of medical intelligent cockpit medical consultation system 5. keywords: cockpit; data; design; medical; system cache: fcis-21121.pdf plain text: fcis-21121.txt item: #325 of 872 id: fcis-21126 author: Lai, Qijie; Ma, Chao; Yin, Qiaoyang; Li, Qiuying; Zhou, Kewei; Ma, Zilin title: Research on the Optimization of Headset Optimization Technology based on Cloud and Edge Computing date: 2024 words: 2245 flesch: 49 summary: At the same time, we have developed a series of sound quality optimization algorithms, and on the edge equipment ( Bluetooth headset) uses streaming technology to test and test the audio data to meet the real -time requirements. 4.8. Experimental data show that through personalized settings, users' satisfaction of sound quality has been improved. keywords: audio; bluetooth; data; edge; processing; quality; sound cache: fcis-21126.pdf plain text: fcis-21126.txt item: #326 of 872 id: fcis-2134 author: Zou, Yixi title: Forecast of COVID-19 Epidemic Trend Based on Multiple Linear Regression Model date: 2022 words: 2632 flesch: 50 summary: In COVID-19 trend forecast model based on multiple linear regression model, there may be multiple variables related to a certain variable y . Keywords: Multiple regression model; COVID-19; Epidemic trend; Forecast. keywords: covid-19; epidemic; forecast; linear; model; regression; trend cache: fcis-2134.pdf plain text: fcis-2134.txt item: #327 of 872 id: fcis-2135 author: Tan, Xiaochuan; Liu, Ruiyuan; Zhang, Shuai; Li, Jiaojiao; Ma, Pengcheng title: Review of pedestrian trajectory prediction methods date: 2022 words: 9370 flesch: 42 summary: Problems and challenges in pedestrian trajectory prediction In recent years, although significant achievements have been made in pedestrian trajectory prediction methods, there are still some problems. According to the modeling method of the prediction model, pedestrian trajectory prediction methods are roughly divided into trajectory prediction methods based on shallow learning and trajectory prediction methods based on deep learning. keywords: attention; computer; conference; data; gan; graph; ieee; interaction; learning; methods; model; motion; network; pedestrian; pedestrian trajectory; prediction; prediction methods; proceedings; social; time; trajectory; trajectory prediction cache: fcis-2135.pdf plain text: fcis-2135.txt item: #328 of 872 id: fcis-2136 author: Zhang, Tongqing; Zhang, Shuai; Ma, Pengcheng; Liu, Ruiyuan; Li, Jiaojiao title: Multi-strategy vertical parking path planning considering the influence of obstacles date: 2022 words: 5247 flesch: 56 summary: In the process of vehicle parking, kinematic constraints mainly consider the maximum angle constraint of vehicle equivalent front wheel and the maximum angle rate constraint of vehicle equivalent front wheel:         Trajectory planning of vehicle parking strategy ll wl EGl EFl 80 Fig. keywords: angle; curve; obstacle; parking; parking path; path; path planning; planning; point; trajectory; vehicle cache: fcis-2136.pdf plain text: fcis-2136.txt item: #329 of 872 id: fcis-21979 author: Zhou, Ji; Bu, Yi title: Research on Natural Disaster Risk Assessment and Insurance Decision-Making Using EWM-TOPSIS and ARIMA Models date: 2024 words: 2703 flesch: 50 summary: Temporal series diagram of risk factors For this set of risk factor time series data need to be ADF test, the unit root statistic corresponds to a p-value significantly greater than 0.05, which is judged to be a non- stationary series, so it is necessary to carry out a first-order difference operation on this column of risk factor data, and then re-plot the time series. Risk factor data after 10 periods of prediction Year Risk Factor 2014 0.6544 2015 0.0768 2016 0.4317 2017 0.2030 2018 0.5710 2019 0.1845 2020 0.1946 2021 0.6630 2022 0.0953 2023 0.3792 3.3. keywords: factors; fig; insurance; method; model; risk cache: fcis-21979.pdf plain text: fcis-21979.txt item: #330 of 872 id: fcis-21988 author: Wang, Yulong; Liu, Xiaobang; Yu, Li; Wang, Chu title: Study on Radiometric Consistency of Landsat Images using Multi-band Joint Regression Model date: 2024 words: 3217 flesch: 46 summary: The relative radiation normalization method is the mainstream research, which is proposed based on the linear relationship between the grayscale values of multi temporal image bands Therefore, by comparing and analyzing the consistency of NDVI values before and after band conversion in different seasons, this article aims to verify the performance and effectiveness of the band conversion model in improving the consistency between bands. keywords: band; consistency; conversion; data; images; model; oli; radiation cache: fcis-21988.pdf plain text: fcis-21988.txt item: #331 of 872 id: fcis-21992 author: Yang, Xu; Zhou , Mingquan; Chen, Chao; Zhong, Weiwei; Yue, Fen title: Semi Solid MR Coal Mine Tunneling Machine Operation Training System date: 2024 words: 2760 flesch: 43 summary: For example, Yu Yang has studied the remote control system of roadheader based on virtual reality technology, with the purpose of improving the efficiency and safety of roadheader operation through high-precision simulation model and remote control technology [6]. Zhang Qianwen proposed a remote virtual automatic cutting control system for roadheader, which uses virtual reality technology to realize unmanned control of the roadheader, and significantly improves the cutting accuracy and operation safety keywords: coal; control; data; machine; operation; system; technology; training cache: fcis-21992.pdf plain text: fcis-21992.txt item: #332 of 872 id: fcis-22001 author: Cao, Yang; Zhang, Meina; Wang, Xianjun; Shang , Yaqin; Jia, Simiao title: Application of Multi-threading Mechanisms to the Connect6 Gaming System date: 2024 words: 2930 flesch: 58 summary: In addition, in the process of game search, hash table and replacement table are used to save the value scores that have been calculated by the nodes, by checking the table to determine whether the node currently searched for exists or not, if it exists directly in the replacement table to obtain the value scores, this method speeds up the search process to a certain extent [2] . Through experimental comparison, it can be obtained that in the field of Connect6 game, the multithreaded search mechanism is more efficient for the position search, and also has better game prediction, which can improve the search efficiency and reduce the search time of Connect6 game to a certain extent. keywords: algorithm; computer; connect6; game; gaming; search; tree cache: fcis-22001.pdf plain text: fcis-22001.txt item: #333 of 872 id: fcis-22002 author: Li , Yian; Huang, Yibo title: End-to-End Speech Hash Retrieval Algorithm based on Speech Content and Pre-training date: 2024 words: 6497 flesch: 53 summary: In order to be able to perform speech retrieval in noisy environments, we manually added Gaussian white noise to the test dataset and constructed speech retrieval tasks with different signal-to-noise ratios (SNRs), including 30 db, 25 db, 20 db, 15 db, and 10 db. Although the use of transcription technology has largely improved the accuracy of speech retrieval, its efficiency and accuracy are highly dependent on advanced speech recognition technology. keywords: content; data; encoder; features; hash; ieee; model; module; performance; pre; recognition; retrieval; speech; speech retrieval; task; training cache: fcis-22002.pdf plain text: fcis-22002.txt item: #334 of 872 id: fcis-22003 author: Lu, Yuxuan title: Research on Multi-Beam Line Finding Problem and Optimal Line Finding Path based on Exhaustion Method date: 2024 words: 3346 flesch: 62 summary: The overlap rate 𝜂𝑖,𝑗 between this line and the previous line 𝑗 − 1 is calculated according to the mathematical model of multi-beam line measurement, so that it meets the extreme value 𝜂𝑖,𝑗 = 0.1 . Research on multi-beam line measurement based on differential algorithm keywords: beam; line; measurement; survey; survey line cache: fcis-22003.pdf plain text: fcis-22003.txt item: #335 of 872 id: fcis-22004 author: Wan, Chaoji; Chen, Chao; Zhong, Weiwei title: Indoor Breeding Environment Monitoring System date: 2024 words: 2418 flesch: 44 summary: This paper aims to explore the application of Internet of Things technology in indoor farming environment monitoring system, analyze its important role in improving farming efficiency and reducing labor costs, and look forward to the future development prospects of intelligent farming system. System function diagram 2.2. keywords: control; data; light; mobile; server; system; test cache: fcis-22004.pdf plain text: fcis-22004.txt item: #336 of 872 id: fcis-22098 author: Zhang, Xude; Luo, Dihong; Wu, Xiaoping title: Based on Raspberry Pi Voice Controlled Smart Home System date: 2024 words: 2524 flesch: 45 summary: Raspberry Pi interfaces connect to the voice module and peripheral modules, serving as the bridge for the normal operation of the entire system. The distribution of Raspberry Pi interfaces is shown in Figure 2. keywords: control; figure; home; module; raspberry; system; voice cache: fcis-22098.pdf plain text: fcis-22098.txt item: #337 of 872 id: fcis-22100 author: Jiang, Lingzhi; Wu, Qiwu; Xie, Zhuoxu title: Risk Assessment of Terrorism in Asia based on K-Means Clustering Analysis date: 2024 words: 2600 flesch: 51 summary: Select the appropriate number of terrorist attack risk levels through the elbow rule, as shown in Figure 2. Distribution of the proportion of countries with intermediate risk events The proportion of countries with low, medium, and high levels of terrorist attack risk is shown in Figures 3 to 5, respectively. keywords: attacks; level; number; principal; risk; terrorist cache: fcis-22100.pdf plain text: fcis-22100.txt item: #338 of 872 id: fcis-22101 author: Nie, Hengli title: Design and Implementation of a Campus Sports Meet Management System date: 2024 words: 2231 flesch: 47 summary: In the user's authority there are information module, competition information module, sports information module. Device management information Click on the loan and return information in the navigation bar to view the overall loan and return information of the equipment, such as who borrowed, lent equipment, lent time and whether to return information. keywords: equipment; information; management; meeting; module; sports; system cache: fcis-22101.pdf plain text: fcis-22101.txt item: #339 of 872 id: fcis-2241 author: Liu, Tong title: Application of Agile Project Management in Software R&D Management of M Enterprise date: 2022 words: 2398 flesch: 48 summary: Therefore, as one of the new methods to break through the traditional software management, agile management method is gradually activated by major software companies and widely used in software project management. Improve agile project management system and guarantee system 4.5.1. keywords: management; methods; product; project; software; team cache: fcis-2241.pdf plain text: fcis-2241.txt item: #340 of 872 id: fcis-2242 author: Liu, Weiqiang; Zhao, Peng; Song, Xiangying; Zhang, Bo title: A Survey of Low-light Image Enhancement date: 2022 words: 4375 flesch: 49 summary: = 𝐼(𝑥)−𝐴 𝑚𝑎𝑥[𝑡(𝑥),𝑡0] + 𝐴 (3) For low light images the reversal of the figure is similar to the fog on the vision chart to this phenomenon, first will get the similar Low-light image reversal after the reversal of the fog figure image, then the transmittance of the pseudo fog figure estimates and atmospheric light will finally solve the parameters into the formula for image restoration, restoration no fog image, further enhanced by low light images. Keywords: Image enhancement; Low-light image dataset; Deep learning; Generative adversarial networks. keywords: enhancement; ieee; image; image enhancement; learning; light; light image; method; network cache: fcis-2242.pdf plain text: fcis-2242.txt item: #341 of 872 id: fcis-22531 author: Yang, Tianhang title: Recognition and Prediction of Precursory Feature Signals of Coal Mine Rock Burst Based on Random Forest and MK Trend Test date: 2024 words: 2612 flesch: 51 summary: In the visualization of data, we show the distribution and trend of data by drawing to help understand 2 the characteristics of data, such as the upward trend of precursor feature data. Precursor Feature Signals Within about 7 days before the earth burst, the electromagnetic radiation and acoustic emission signals have a tendency to increase with time cycle, which is called precursor characteristic signals. keywords: data; precursor; signal; test; time; trend cache: fcis-22531.pdf plain text: fcis-22531.txt item: #342 of 872 id: fcis-22533 author: Guan, Boyang title: Analysis of Natural Gas Hydrate Resource Content based on Kriging Algorithm and TOPSIS Evaluation Model date: 2024 words: 3931 flesch: 43 summary: Range of natural gas hydrate resources 12 The range of natural gas hydrate resource distribution is solved as shown in Fig. Introduction At present, the exploration and evaluation system of natural gas hydrate resources is still imperfect, and the research on the evaluation method of natural gas hydrate resources is an important part of the theoretical research on natural gas hydrate, which is the key to effectively guide the exploration and development activities of natural gas hydrate. keywords: evaluation; gas; gas hydrate; hydrate; point; resources; value cache: fcis-22533.pdf plain text: fcis-22533.txt item: #343 of 872 id: fcis-22555 author: Xu, Luyao title: Service Performance in Banks: The Effects of Customer Relationship Management Systems Extended Usage date: 2024 words: 6552 flesch: 43 summary: The results show that employee CRMS explorative usage has a positive impact on their service performance, while employee CRMS exploitative usage has a significant negative impact on service performance. Therefore, we intend to explore the motivator and the consequences of employee CRMS extended usage (i.e., exploitative usage and explorative usage behaviors) in this study. keywords: behaviors; crms; customer; efficacy; employees; information; leader; leadership; model; performance; service; service performance; usage cache: fcis-22555.pdf plain text: fcis-22555.txt item: #344 of 872 id: fcis-22590 author: Jiang , Lingzhi; Wu , Qiwu; Tan, Weicong; Tong, Tao; Zhang, Weiyi title: Research on Unmanned Aerial Vehicle Path Planning date: 2024 words: 1883 flesch: 43 summary: Combining the characteristics of various algorithms, classical search algorithms are suitable for path planning in static environments; evolutionary algorithms are suitable for complex path planning problems and have better global search capabilities; heuristic-based search algorithms combine heuristic information to guide the search direction, and are suitable for path planning problems that require efficient search; and deep learning methods are suitable for path planning problems in large-scale data and complex environments . Abstract: This paper reviews and analyses the research progress in the field of UAV path planning. keywords: algorithms; optimization; path; planning; search; uav cache: fcis-22590.pdf plain text: fcis-22590.txt item: #345 of 872 id: fcis-22596 author: Li, Xinyao title: Overview of Trust-region Methods date: 2024 words: 2646 flesch: 44 summary: Recent developments in algorithms and software for trust region methods (pp. 258–287). Trust regions control the size of the steps taken in the inner-point phase, ensuring that the iteration remains close to the feasible regions. keywords: confidence; method; optimization; region; step; trust cache: fcis-22596.pdf plain text: fcis-22596.txt item: #346 of 872 id: fcis-22600 author: Guo, Haixi; Liu, Shasha title: Teaching Skills Cultivation of Information Technology Normal University Students from the Perspective of Group Intelligence: Research on the Training and Application Optimization of GPT Dialogue Model date: 2024 words: 3389 flesch: 35 summary: Uneven of educational resources: In some areas, information technology teaching resources are insufficient, school facilities and teaching equipment are limited, and teachers are insufficient, leading to uneven quality of information technology teaching. Through the teaching mode from the perspective of group wisdom, normal university students can have more in-depth interaction and cooperation with classmates, teachers and teaching resources, and promote the innovation and improvement of information technology teaching. keywords: education; group; information; model; students; teaching; technology cache: fcis-22600.pdf plain text: fcis-22600.txt item: #347 of 872 id: fcis-22603 author: Li, Sixian title: Research on The Innovative Development of Digital Media Art in The Era of Artificial Intelligence date: 2024 words: 2884 flesch: 34 summary: Digital media art relies on digital media technology to artistically display creativity, which has a profound impact and is crucial to the development and growth of cultural and creative industries. In order to explore the characteristics and future development of digital media art, this article uses interdisciplinary research methods, comparative research methods, literature research methods, etc. to understand the relationship between digital media technology and artificial intelligence, from the perspectives of technology, communication, and art Let’s observe the current performance of digital media art as it becomes more and more intelligent, find out the problems and solutions hidden under the wave of intelligence, and explore the innovative development strategies of digital media art. keywords: art; development; industries; industry; intelligence; media; research; technology cache: fcis-22603.pdf plain text: fcis-22603.txt item: #348 of 872 id: fcis-22610 author: Gao, Haipeng; Teng, Yadong title: Contrastive Prediction and Estimation of Deformable Objects based on Improved Resnet date: 2024 words: 4979 flesch: 55 summary: The emergence of contrast learning method based on self supervised learning not only reduces the training cost of images and labels, but also can extract a general and easy to transform feature model. Estimating model utility for deformable object manipulation using multiarmed bandit methods. keywords: data; encoder; extraction; feature; information; learning; manipulation; method; model; network; objects; samples; space; state cache: fcis-22610.pdf plain text: fcis-22610.txt item: #349 of 872 id: fcis-22613 author: He, Huiqian; Tan, Yihao; He, Yuan; Xu, Qianwen; Yang, Taotao; Peng, Xiaojiang title: Design of Telemedicine Service System for the Elderly from the Perspective of Active Aging date: 2024 words: 2827 flesch: 43 summary: What are the user pain points and needs of the elderly for telemedicine service systems? As a special user group, the elderly have unique and diverse needs for telemedicine service systems. keywords: aging; design; health; medical; needs; service; system; telemedicine; user cache: fcis-22613.pdf plain text: fcis-22613.txt item: #350 of 872 id: fcis-22616 author: Ao, Liu; Zhang, Xude; Wang, Piaoyun; Wang, Ruiwen; Jia, Zhengju title: Research on Wearable Devices Based on the Internet of Things date: 2024 words: 2183 flesch: 53 summary: Overall Structural Design This wearable device is an intelligent wearable product designed on the basis of the convenient mode of high-speed transmission of data information through the Internet of Things. China Abstract: Wearable devices are closely related to people's lives. keywords: circuit; data; design; device; figure; module; system cache: fcis-22616.pdf plain text: fcis-22616.txt item: #351 of 872 id: fcis-22622 author: Niu , Shitan title: Study on Pricing and Replenishment of Vegetable Commodities based on TOPSIS and ARIMA Models date: 2024 words: 3252 flesch: 53 summary: Correlation coefficients between categories Foliage Mushroom Aquatic root Cabbage Pepper Eggplant Foliage 1 ∗∗∗ 0.502 ∗∗∗ 0.301 ∗∗∗ 0.5 ∗∗∗ 0.571 ∗∗∗ 0.471 ∗∗∗ Mushroom 0.502 ∗∗∗ 1 ∗∗∗ 0.626 ∗∗∗ 0.329 ∗∗∗ 0.3 ∗∗∗ 0.099 ∗∗ Aquatic root 0.301 ∗∗∗ 0.626 ∗∗∗ 1 ∗∗∗ 0.064 0.08 ∗ 0.155 Correlation Analysis Considering that category sales are continuous variables that change over time, Pearson's correlation coefficient and Spearman's correlation coefficient are considered for correlation analysis. keywords: categories; coefficient; correlation; sales; time; volume; ∗∗∗ cache: fcis-22622.pdf plain text: fcis-22622.txt item: #352 of 872 id: fcis-22624 author: Huang, Yibo; Sun, Guoli; Huang, Xiaoyin; Lin, Cen; Li, Hang title: Study on the Development of Property Insurance Industry Based on ARIMA and CGDAM-WRIR Models date: 2024 words: 3909 flesch: 45 summary: The application of ARIMA modeling helps us to assess the potential losses that may be caused by future extreme weather events, predict the mortality rate, and evaluate the impacts of tornadoes of varying intensities in different regions, which provides an important reference for risk management and underwriting strategy provides an important reference. Abstract: This study aims to address the climate change challenges faced by the property-casualty insurance industry by using the ARIMA model to assess the potential impacts of extreme weather events on the insurance industry and the CGDAM-WRIR model to analyze the regional impacts of tornadoes and the impacts of climate change on communities. keywords: arima; data; events; insurance; model; series; time; weather cache: fcis-22624.pdf plain text: fcis-22624.txt item: #353 of 872 id: fcis-22628 author: Wang, Ning; Hou, Xiaojun; Ma, Jikun; Yuan, Bingbing; Xin, Fuyan title: Research on Big Data Intelligent System for Fault Diagnosis of Computer Aided Ship Power System date: 2024 words: 3981 flesch: 39 summary: In the stage of building fault diagnosis model, the research team carefully selected representative fault sample 68 data based on actual fault cases for training and verifying the intelligent fault diagnosis model that integrates machine learning and deep learning algorithms. Secondly, in view of the nonlinear and time-varying characteristics of ship power system faults, this study designs and implements a fault diagnosis model that integrates intelligent algorithms such as machine learning and deep learning. keywords: accuracy; data; diagnosis; fault; model; power; power system; ship; system cache: fcis-22628.pdf plain text: fcis-22628.txt item: #354 of 872 id: fcis-23012 author: Chen, Ang; Huang, Rongzhao; Xi, Tong; Wu, Liang; Bianba, Wangdui title: Emotion Recognition in Lhasa Tibetan Speech based on Bi-LSTM Graph Convolutional Networks date: 2024 words: 3093 flesch: 56 summary: Based on the foundation of constructing a TBLS1 dataset containing 6,000 Tibetan-language speech samples, an approach was devised for Tibetan speech emotion recognition. In today’s increasingly intelligent and automated technological context, speech emotion recognition plays an important role in human-computer interaction and is an important way for artificial intelligence to understand human emotions keywords: emotion; graph; information; loss; node; recognition; speech; tibetan cache: fcis-23012.pdf plain text: fcis-23012.txt item: #355 of 872 id: fcis-23013 author: Kang, Haoqing; Gao, Jian; Wang, Shicong; Zhou, Kanglei; Huang, Chuanyi title: Research on Stability of Tower Crane based on ANSYS Software date: 2024 words: 3965 flesch: 53 summary: Abstract: In order to strengthen the safety management of tower cranes on construction sites and prevent accidents caused by the deformation of the standard section of tower cranes during the construction process, in response to the stability of the WA6013-6A tower crane operation process, the static analysis of the standard section structure and attachment method during the lifting process of tower cranes was carried out using Ansys software, and the maximum displacement and stress-strain situation of tower cranes with different tower crane heights and attachment distances were obtained. The results show that the more attached the tower crane is, the higher the standard section stress dispersion and the continuous decrease in effective stress; The smaller the distance between connecting walls, the more connecting components there are, the smaller the standard deformation rate of tower cranes, and the better the stability of tower cranes. keywords: attachment; crane; maximum; spacing; standard; stress; tower; tower crane cache: fcis-23013.pdf plain text: fcis-23013.txt item: #356 of 872 id: fcis-23014 author: Yang, Dongxu; Huo, Ran; Jia, Jingquan; He, Linxuan title: Research on Equipment Fault Identification Method and System based on Big Data Correlation Analysis date: 2024 words: 2644 flesch: 43 summary: This system achieves precise identification of equipment faults by finely collecting and preprocessing equipment operation data, deeply exploring potential association rules between data. Association rule mining: Using association analysis algorithms to mine feature vectors and discover association rules between equipment operation data and faults. keywords: analysis; data; equipment; identification; model; monitoring; prediction; system; time cache: fcis-23014.pdf plain text: fcis-23014.txt item: #357 of 872 id: fcis-23016 author: Zou, Zheng; Zhu, Peixuan; Fu, Tianli title: Research on a Machine Vision-based Blade Measurement Method date: 2024 words: 2825 flesch: 48 summary: As shown in Figure 12, the irregular arrangement of edge points in the upper left corner of the blade after processing is not conducive to the subsequent fitting of edge lines. This enhances the accuracy of blade edge positioning and consequently improves blade measurement precision. keywords: blade; calibration; edge; image; measurement; pixel; points cache: fcis-23016.pdf plain text: fcis-23016.txt item: #358 of 872 id: fcis-23018 author: Gao, Cong; Sun, Mingge; Guo, Xiaolong; Li, Yinggang; Zhang, Xingke title: Simulation Application of BPNN-PID Controller with Improved Ant Colony Algorithm in Temperature Control System date: 2024 words: 3433 flesch: 56 summary: In recent years, in order to improve the performance of temperature control system, many experts and scholars are committed to applying various advanced control algorithms to temperature control. China Abstract: Aiming at the nonlinear and hysteresis of PID controller in temperature control, this paper proposes a BPNN-PID control scheme with improved ant colony algorithm, and uses MATLAB to simulate and compare experiments. keywords: algorithm; ant; bpnn; colony; control; controller; pid; system; temperature cache: fcis-23018.pdf plain text: fcis-23018.txt item: #359 of 872 id: fcis-23019 author: Liu, Shasha; Guo, Haixi title: Research on the Current Situation of Teachers' Digital Literacy date: 2024 words: 5087 flesch: 31 summary: The Training Content and Mode of Teachers' Digital Literacy are Old Most areas of teacher digital literacy training in China are surface, Not on the basis of the subjects, In the first line of practice, On the basis of teachers, considering the content and mode of their training, There is on paper, Unpractical and other issues, When teachers don't want to train, I think the training is time-consuming and laborious and meaningless to my teaching, It is difficult to apply it to the practice of all subjects, So, right now, Change to the content of the training, Reduce the scale of the training, Training and teaching with subject and background knowledge, Changing the traditional ways of teacher training, Pay more attention to it in your daily life, subtly changing teachers' digital literacy, Teaching also uses online and offline use, Design the development of the classroom way, Gradually changing the teachers' stereotype of teacher training, Fundamentally solve the problems of teachers in teaching, Improve teachers' digital literacy[19]. This paper makes a comprehensive analysis of the research results of teachers' digital literacy through the literature review method and the retrieval and analysis of the relevant literature at home and abroad. keywords: ability; development; digital; education; evaluation; literacy; professional; research; teachers; teaching; technology; training cache: fcis-23019.pdf plain text: fcis-23019.txt item: #360 of 872 id: fcis-23824 author: Cao, Enqi; Bu, Fanliang; Han, Zhuxuan title: AutoEncoder-Based Data Completion Model for Theft Cases of Items Inside Cars date: 2024 words: 2988 flesch: 50 summary: Experimental results show that RepConv-RNN-AE can effectively complete the missing values in car interior theft case data and demonstrates superiority in completing missing data in car interior theft cases. Although car interior theft case data is essentially one- dimensional, the location information can still be transformed into multidimensional features through one-hot encoding. keywords: car; case; data; feature; rnn; theft cache: fcis-23824.pdf plain text: fcis-23824.txt item: #361 of 872 id: fcis-23825 author: Chen, Bo; Cao, Tuokai; Yao, Lidong title: Research on Short-Term Multi-Step Prediction of River Dissolved Oxygen based on STL-LSTM date: 2024 words: 4821 flesch: 61 summary: Li C et al. (2018) used the wavelet method to denoise the dissolved oxygen data and experimentally demonstrated that the LSTM model is more suitable for dissolved oxygen prediction compared to traditional chaotic time series models. A hybrid model for dissolved oxygen prediction in aquaculture based on multi- scale features. keywords: accuracy; lstm; model; oxygen; prediction; series; step; stl; strategy; time cache: fcis-23825.pdf plain text: fcis-23825.txt item: #362 of 872 id: fcis-23827 author: Cheng, Kong title: Internet of Things (IoT) Computer Network Security and Its Remote Control Technology: Key Points and Applications date: 2024 words: 1719 flesch: 37 summary: The application layer is responsible for information processing in the system, analyzing a large amount of data deeply to mine valuable information content. By restoring various data packets to their original data segments, centralized processing of various data information can be achieved. keywords: control; information; network; processing; security cache: fcis-23827.pdf plain text: fcis-23827.txt item: #363 of 872 id: fcis-23828 author: Lyu, Guangqiang; Xie, Yanjing title: Research on Optimization Method of Dredging Robot based on Deep Learning date: 2024 words: 1975 flesch: 46 summary: Deep learning and PID controller trajectory comparison After further analysis of the error situation found that after 1000 training of deep reinforcement learning model can track error stability control within 0.02m, and the maximum error of the PID controller is close to 0.04m, and the error fluctuation is more obvious, shows the deep reinforcement learning in the advantage of track tracking, and provide valuable reference for research and application in related fields. Deep learning models can learn and improve trajectory planning strategies based on historical data and real-time feedback keywords: dredging; learning; network; robot; trajectory cache: fcis-23828.pdf plain text: fcis-23828.txt item: #364 of 872 id: fcis-23836 author: Chen, Sihan title: Optimization of User Experience Design Process Driven by AIGC date: 2024 words: 2564 flesch: 43 summary: This paper delves into the application of AIGC in user experience design, demonstrating its great potential in optimizing the design process and enhancing user experience. Next, personalized recommendations, customized pages, and other designs are implemented to meet users' individual needs and improve the quality of user experience based on user data and behavior analysis. keywords: aigc; data; design; experience; intelligence; process; technology; user cache: fcis-23836.pdf plain text: fcis-23836.txt item: #365 of 872 id: fcis-23843 author: Li, Yang; Zou, Yanchen; Xu, Haoqi title: From Data to Decisions: The Integration of AI in Epidemiological Research date: 2024 words: 4818 flesch: 40 summary: 3. AI analysis: AI models in the cloud platform analyze ECG data in real-time, detecting abnormal signals such as arrhythmias and tachycardia 4. Not only these models are commonly utilized in academic and industrial spheres but also perform well when dealing with health data. keywords: accuracy; analysis; data; disease; health; machine; model; research; use cache: fcis-23843.pdf plain text: fcis-23843.txt item: #366 of 872 id: fcis-23848 author: Cheng, Yan title: Exploration and Practice of Parallel Logistics and Transportation System Basing on AI date: 2024 words: 1921 flesch: 30 summary: With the continuous advancement of globalization and information technology, logistics and transportation system are playing an increasingly important role in modern society. In the modern supply chain management system, the data sharing and integration between parallel logistics and transportation system is very important. keywords: logistics; system; technology; traffic; transportation cache: fcis-23848.pdf plain text: fcis-23848.txt item: #367 of 872 id: fcis-23856 author: Qin, Xinpeng title: Water Quality Image Recognition based on SVM date: 2024 words: 3655 flesch: 53 summary: Firstly, python is used to extract the features of water sample image, the data were pre-processed, divided into training and test sets, and the SVM is used to construct water quality classification models. 2. Image Preprocessing When using color features to recognize water quality image, the color information carried by color image is especially rich, which can describe the surface color features of water samples more accurately. keywords: classification; color; data; image; model; order; quality; water; water quality cache: fcis-23856.pdf plain text: fcis-23856.txt item: #368 of 872 id: fcis-23857 author: Qian, Junyi title: Optimization Study on the Evaluation and Design of College Students' Dietary Recipes based on the Planning Model date: 2024 words: 2399 flesch: 53 summary: Since the constraints of male university students and female university students and the establishment of objective function ideas are basically the same, but there are different data in the principle of recipe optimization design, the following constraints are set according to the standard data of male university students. For the specific algorithm implementation, consider the use of particle swarm algorithm, define the particle swarm internal value, add constraints, to obtain the optimal solution, the obtained a reasonable recipe for male university students is shown in Table 1, the same for female university students. keywords: acid; amino; diet; model; score; students cache: fcis-23857.pdf plain text: fcis-23857.txt item: #369 of 872 id: fcis-24157 author: Wan, Hailu; Zhou, Hua; Chen, Siyu title: Research on the Countermeasures of Cultural and Tourism + Artificial Intelligence to Improve Rural Revitalization in Guangxi date: 2024 words: 6282 flesch: 20 summary: This research focuses on cultural tourism + artificial intelligence to empower rural tourism, and brings a new experience to tourists by creating characteristic cultural tourism products and building a smart cultural tourism system. As an important engine of rural revitalization, rural tourism has rich cultural and ecological resources, but the traditional model has problems such as serious homogenization competition, insufficient tourist experience and weak industrial chain. keywords: application; culture; development; experience; guangxi; integration; intelligence; resources; revitalization; technology; tourism cache: fcis-24157.pdf plain text: fcis-24157.txt item: #370 of 872 id: fcis-24158 author: Zhong, Fangyuan title: Design of Flexible RFID Tag Antenna Suitable for Aviation Material Management date: 2024 words: 1291 flesch: 59 summary: Acknowledgments The funds: Chengdu College of University of Electronic Science and Technology of China pre-research project Research on UHF RFID tag antenna for aviation maintenance and aviation material management (2023- KXYJ-29). In the design process of tag antennas, the recognition distance of the tag antenna is one of the important performance parameters. keywords: antenna; frequency; rfid; tag; uhf cache: fcis-24158.pdf plain text: fcis-24158.txt item: #371 of 872 id: fcis-24159 author: Zhang, Ying; Zhou, Min; Guo, Wenxuan; Zhu, Ruiqi; Liufu, Jieyu; Lin, Jiawei; Li, Zhengtao title: Algorithm Analysis and Design Python Teaching Examples of Recursive and Partitioning Algorithms date: 2024 words: 1745 flesch: 60 summary: Example problem: The Fibonacci sequence, derived from a rabbit breeding problem in the famous work Liber Abaci by the Italian mathematician Fibonacci, is a sequence: Example problem: Like-minded book friends. keywords: algorithms; conquer; divide; problem cache: fcis-24159.pdf plain text: fcis-24159.txt item: #372 of 872 id: fcis-24160 author: Yao, Tianchen title: A Delayed Mathematical Model of Population Pressure on the Atmospheric Level of Carbon Dioxide Gas date: 2024 words: 6998 flesch: 74 summary: Then, we obtain 1 0 ( ) cos( ) ( )     =  (8) 2 0 ( ) sin( ) ( )     =  (9) where 8 2 6 2 2 4 0 3 2 2 0 2 1 3 2 2 2 2 2 1 0 2 0 2 1 0 0 ( ) ( 2 ) ( 2 2 ) ( 2 2 ) , F F F F H F F F F F H H H F H       = + − + + − − + − + − + − 6 4 1 2 3 3 1 3 2 2 2 0 3 1 1 2 2 0 0 0 2 2 1 1 1 0 0 0 ( ) ( ) ( ( ) ( )) ( ( ) ( ) ( )) ( ), G G F G F G F H G G H F G F H G F H G H F G F H      = − + − − − − − + − + − + − + − 7 5 3 3 2 3 1 3 2 2 3 1 2 2 3 0 0 2 1 1 0 3 0 1 1 1 0 0 ( ) ( ( )) ( ( ) ( ) ( ) ) ( ( ) ( )) . 3 0 11 22 44F f f f= − − − , 1 0 21 44 14 42 0 11 22 44 44 22( ) ( )G f g f g f f g f g  = keywords: f f; f g; g g; h f; t f; − −; − ;  ;   cache: fcis-24160.pdf plain text: fcis-24160.txt item: #373 of 872 id: fcis-24299 author: Liu, Dong; Xin, Peng; Wen, Xiaoqiang title: Reliability Evaluation of Nonlinear Degraded Equipment based on Wiener Process date: 2024 words: 2798 flesch: 47 summary: This technique utilizes the Wiener process to depict equipment degradation and employs a time scale model to linearize nonlinear data. In order to consider the degradation differences between individuals, We introduce a method for evaluating equipment reliability in the context of nonlinear degradation, leveraging the Wiener process. keywords: degradation; equipment; model; nonlinear; process; reliability; wiener cache: fcis-24299.pdf plain text: fcis-24299.txt item: #374 of 872 id: fcis-24300 author: Liang, Di; Lin, Zhongming; Su, Xiangyun; Li , Wenjing; Wen, Biaotang; Chen, Zhendong; Guo, Yuanyuan; Chuah, Y.D. title: Intelligent Planting of Subtropical Fruits and Vegetables based on Artificial Intelligence date: 2024 words: 4261 flesch: 34 summary: The intelligent water and fertilizer management system based on AI and visual recognition can establish an accurate water and fertilizer demand forecasting model by analyzing multi-source data such as crop growth data, soil environment information and meteorological conditions, and realize accurate supply and on-demand distribution of water and fertilizer. The establishment begins with the fine annotation of massive image data, aiming to clearly mark the growth stages of fruits and vegetables, subtle changes in leaf color, and specific symptoms of pests and diseases, so as to provide a solid data foundation for subsequent model training. keywords: data; decision; fertilizer; fruit; growth; management; model; recognition; system; technology; water cache: fcis-24300.pdf plain text: fcis-24300.txt item: #375 of 872 id: fcis-2482 author: Bao, Hao title: Homomorphic computing of encrypted data outsourcing in cloud data center date: 2022 words: 1979 flesch: 59 summary: Keywords: Cloud data center; Data encryption; Data outsourcing; Homomorphic computing. Frontiers in Computing and Intelligent Systems ISSN: 2832-6024 | Vol. 2, No. 1, 2022 1 Homomorphic computing of encrypted data outsourcing in cloud data center Hao Bao College of Electronic and information, Southwest Minzu University Chengdu 610041, Sichuan, keywords: cloud; data; e(𝑚1; vol cache: fcis-2482.pdf plain text: fcis-2482.txt item: #376 of 872 id: fcis-2483 author: Chen, Qingguo title: Application and Development Trend of Computer Science in Face Completion date: 2022 words: 2115 flesch: 43 summary: At this time, this generative confrontation network can meet the technical requirements of face image restoration technology. By extracting the feature vector of face image to high-dimensional space, the vector is segmented in high-dimensional space, and then repaired and recognized. keywords: face; image; network; technology cache: fcis-2483.pdf plain text: fcis-2483.txt item: #377 of 872 id: fcis-2484 author: Zhu, Yizhang title: Open Chinese Internet Sarcasm Corpus Construction: An Approach date: 2022 words: 2623 flesch: 55 summary: Their reports and commentaries are serious no matter pro or con standpoints, and hardly sarcastic or ironic, which are suitable as non-sarcastic materials. Gong et al. constructed a corpus containing 2,486 manually selected and annotated sarcastic texts collected from Guanchazhe which means observers, a Chinese integration website of news and commentary. keywords: chinese; corpus; data; non; sarcasm; texts cache: fcis-2484.pdf plain text: fcis-2484.txt item: #378 of 872 id: fcis-2485 author: Wu, Tianhao title: Review of RSSI-based Positioning Algorithm and Accuracy date: 2022 words: 2738 flesch: 41 summary: In addition, most of today's research on RSSI localization has been improved on the basis of the original RSSI algorithm, which has more optimization directions from the principle, which are analyzed and classified in this paper to provide some entry points and help for others' research. For example, BP neural networks were used to optimize RSSI ranging algorithms by Yao et al, a research group that proposed a ranging method that applied a BP neural network model based on the K-means clustering algorithm, divided the distance intervals for the sample data during ranging, fed the classified data into the neural network, built the model and calculated the measured distances. keywords: accuracy; algorithm; filtering; localization; model; positioning; rssi cache: fcis-2485.pdf plain text: fcis-2485.txt item: #379 of 872 id: fcis-2486 author: Wang, Xinyu; Zhang, Jing title: Lightweight Multi-Attention Fusion Network for Image Super-Resolution date: 2022 words: 5450 flesch: 56 summary: Image super-resolution using very deep residual channel attention networks[C]//Proceedings of the European conference on computer vision (ECCV). Comparison with state-of-the-art Methods To prove the effectiveness of the proposed method for image super-resolution, we visualize the partially reconstructed images of B100 and Urban100 datasets. keywords: attention; channel; computer; conference; features; image; information; network; pooling; resolution; super; vision cache: fcis-2486.pdf plain text: fcis-2486.txt item: #380 of 872 id: fcis-2487 author: Zhang, Juan; Lv, Taizhi title: Design and implementation of ship data analysis platform date: 2022 words: 1706 flesch: 51 summary: As an important component, ship data provides a strong guarantee to meet this demand. Keywords: Ship data; Maritime management; Spring Cloud; Data visualization; Vue; MySQL. keywords: data; end; management; maritime; ship; statistics cache: fcis-2487.pdf plain text: fcis-2487.txt item: #381 of 872 id: fcis-2488 author: Feng, Wenyue; Xuan, Shuangxia title: Initial Cluster Centers Based on Moving Two Lines Approximation in K-means Algorithm date: 2022 words: 1812 flesch: 64 summary: Keywords: Initial cluster centers; Moving two lines approximation; K-means algorithm. Kkan and Ahmad propose an algorithm to compute initial cluster centers for k- means clustering. keywords: algorithm; centers; cluster; means cache: fcis-2488.pdf plain text: fcis-2488.txt item: #382 of 872 id: fcis-2489 author: Wang, Mengyuan; Li, Chunqing title: Research of BP Neural Network Based on GA-WOA Algorithm Optimization in MBR Membrane Pollution Simulation date: 2022 words: 1798 flesch: 48 summary: Comparison of model prediction errorst Figure 4 shows the prediction error of WOA-BP neural network model and GA-WOA hybrid algorithm to optimize BP neural network model. Keywords: BP neural network; GA-WOA hybrid algorithm; MBR system. keywords: algorithm; membrane; network; neural; woa cache: fcis-2489.pdf plain text: fcis-2489.txt item: #383 of 872 id: fcis-2490 author: Xu, Shiwei title: Coastal Wind Power Forecasting Research Scheme Design date: 2022 words: 4896 flesch: 46 summary: However, LSTM still has the following shortcomings in wind power prediction: (i) hidden features in the data are more important than usual during extreme weather or large power fluctuations, but LSTM cannot identify the differences of these high-dimensional features; (ii) in the face of multi- dimensional long series of wind power data, there are problems such as easy to ignore the sequence structure information and difficult to solve the long-time dependence. Firstly, wind power forecasting provides a basis for coastal wind farms to make operation plans and grid dispatching departments to adjust dispatching plans, thus alleviating the impact of wind power access on the grid and ensuring the efficient and stable operation of the power system. keywords: data; forecasting; meteorological; method; model; power; prediction; research; term; time; wind; wind power cache: fcis-2490.pdf plain text: fcis-2490.txt item: #384 of 872 id: fcis-25094 author: Huang, Xuan; Huang, Linyi; Tong, Guowei; Zhou, Xundao; Luo, Jianheng title: Security Challenges and Reflections on Large Models date: 2024 words: 2303 flesch: 31 summary: Carry out small-scale pilot projects for vertical large models in fields such as automotive, manufacturing, and healthcare, explore sandbox regulatory mechanisms, and provide public resource technical support and testing evaluation services such as computing power, algorithms, and data to enhance the accuracy, professionalism, safety, and credibility of large models and their applications in vertical fields. This paper discusses the emergence of the Hundred Model War and the significant growth in large models, highlighting the potential for transformative applications in vertical fields such as automotive, medical, and finance. keywords: applications; artificial; development; evaluation; industry; intelligence; models; security; technology cache: fcis-25094.pdf plain text: fcis-25094.txt item: #385 of 872 id: fcis-25095 author: Bian, Jinhua; Zhang, Xiaoxia title: A Hill-Climbing Differential Evolutionary Algorithm for solving Multiple Travelling Salesman Problem date: 2024 words: 2806 flesch: 41 summary: Table 1 gives the optimal paths generated by DE algorithm, HCA algorithm and HCA&DE algorithm under the test of dataset with city size of 51,100,150. Step3: Select city solution sets from the current population and perform DE algorithm crossover operation with mutated individuals to generate new city solution paths and calculate the fitness of new solutions. keywords: algorithm; crossover; hca&de; opt; search; solution cache: fcis-25095.pdf plain text: fcis-25095.txt item: #386 of 872 id: fcis-25096 author: Yang, Zhiwei title: Improved Particle Swarm Optimization Algorithm for Mobile Robot Path Planning date: 2024 words: 3464 flesch: 54 summary: China Abstract: In solving the path planning problem of multi-path robots, an improved particle swarm optimization algorithm is proposed to address the drawbacks of premature convergence and low search accuracy of particle swarm optimization algorithm. Although particle swarm optimization algorithm is easy to use, it requires a large number of parameters to be set, which is not conducive to finding the optimal parameters. keywords: algorithm; optimization; particle; path; planning; position; pso; search; swarm cache: fcis-25096.pdf plain text: fcis-25096.txt item: #387 of 872 id: fcis-25097 author: Liu, Meixi title: AIGC Enabling the Transformation and Upgrading of Theatre Arts Designs date: 2024 words: 3129 flesch: 38 summary: China Abstract: This paper discusses the innovative application and far-reaching impact of AIGC technology in the field of stage art design, which focuses on how AIGC can be the core driving force to accelerate the transformation of stage art design from traditional paradigm to intelligent and interactive. Through the comprehensive literature review, in-depth analysis of technology, and typical case studies, this paper comprehensively comprehends the core concepts and types of AIGC technology, as well as its latest application progress in stage art design. keywords: aigc; art; choreography; design; digital; new; stage; technology cache: fcis-25097.pdf plain text: fcis-25097.txt item: #388 of 872 id: fcis-25098 author: Tang, Zheng; Jiang, Zhengwei; Li, Ying; Yuan, Haowei; Han, Jiayu; Chen, Chao title: Research on the Association Analysis of Online Learning Behaviors Based on the Apriori Algorithm date: 2024 words: 4025 flesch: 44 summary: Bai Jieqiong et al.[3] explored student collaborative learning behavior patterns using lag sequential analysis (LSA), finding that collaborative learning promotes higher-order thinking and knowledge construction, clarifying the key behavioral sequences of effective collaborative learning and providing specific guidance for teachers. Considering that these records do not reflect typical student behavior, the team removed such outliers from the data set to focus on the analysis of true student learning behaviors. keywords: algorithm; analysis; association; behavior; data; learning; online; students; submission; support cache: fcis-25098.pdf plain text: fcis-25098.txt item: #389 of 872 id: fcis-25099 author: Zhao, Jingwei; Zhao, Hui; Tao, Ye title: Research on the Application of Municipal Solid Waste Classification Based on Big Data date: 2024 words: 2961 flesch: 32 summary: In addition, we need to continue to deepen the integration of big data technology and garbage classification business, and promote the in-depth development of garbage classification through technological innovation and model innovation. For the general public, the implementation of big data technology will facilitate the process of garbage classification, thereby enhancing their willingness to engage in this activity. keywords: analysis; classification; collection; data; garbage; management; technology; waste cache: fcis-25099.pdf plain text: fcis-25099.txt item: #390 of 872 id: fcis-25100 author: Liu, Tianqi; Zhang, Zhao title: Design and Application of Greenhouse Intelligent Control System date: 2024 words: 2386 flesch: 46 summary: The application of greenhouse environment intelligent control system not only saves energy, but also improves work efficiency and reduces human error. The main flowchart of the system is shown in table 1. (2) Temperature and Humidity Sensor Modules DHT11 adopts a single bus design, after STM32 starts to start, DHT11 starts to collect temperature and humidity data, when the current ambient temperature and humidity does not change, the OLED display shows the data directly, and when it detects the change of the current ambient temperature and humidity, it re-collects the temperature and humidity data and displays it. keywords: data; environment; humidity; light; sensor; system; technology; temperature cache: fcis-25100.pdf plain text: fcis-25100.txt item: #391 of 872 id: fcis-25103 author: Miao, Lu; Li, Weibo; Zhao, Jia; Zhou, Xin; Wu, Yao title: Differential Private Defense Against Backdoor Attacks in Federated Learning date: 2024 words: 7237 flesch: 62 summary: However, the training process of federated learning is vulnerable to adversarial attacks (e.g., backdoor attack) in presence of malicious clients. Previous works showed that differential privacy (DP) can be used to defend against backdoor attacks, at the cost of vastly losing model utility. keywords: accuracy; attack; backdoor; clients; learning; model; privacy; rate; success; training cache: fcis-25103.pdf plain text: fcis-25103.txt item: #392 of 872 id: fcis-25104 author: Liang, Kaicheng; Yan, Luotao; Wei, Weixin; Qiao, Liangjie; Wang, Hao title: Design of Photovoltaic Solar Panel Intelligent Tracking System based on 51 Single Chip Microcomputer date: 2024 words: 1816 flesch: 52 summary: Stepper motor physical picture This system uses stepper motor to control rotation. The intelligent tracking system of photovoltaic solar panel based on 51 single chip microcomputer designed in this paper can effectively improve the utilization efficiency of solar energy through real-time monitoring of photoresistor and intelligent control of stepper motor. keywords: light; motor; photoresistor; photovoltaic; system cache: fcis-25104.pdf plain text: fcis-25104.txt item: #393 of 872 id: fcis-25105 author: Wang, Yilin title: Projection Methods for 360-degree Video date: 2024 words: 3359 flesch: 52 summary: In order to reduce the transmission bandwidth of panoramic video, the common processing methods are Equirectangular Projection and Cube Projection and so on. Although these projection methods can reduce the transmission bits of panoramic video, the bandwidth and playback complexity of panoramic video are still much larger than traditional video. keywords: cube; equirectangular; image; projection; smoothing; video cache: fcis-25105.pdf plain text: fcis-25105.txt item: #394 of 872 id: fcis-25106 author: Du, Jiale title: Soft Fluidic Actuators, Fluidic Sensors and Their Integration System date: 2024 words: 4763 flesch: 28 summary: Moreover, Yu et al. emphasized the importance of multifunctionality in soft actuators and proposed a methodology for achieving multifunctional liquid crystal polymer network soft actuators via direct injection of functional components[41]. Lan et al. concentrated on the design and fabrication of light-driven liquid crystalline networks and soft actuators featuring controlled molecular motors, thereby underscoring their potential in fostering the development of untethered intelligent soft robots and advanced functional devices[42]. keywords: actuators; applications; control; et al; hydraulic; integration; robotics; sensors; soft; systems cache: fcis-25106.pdf plain text: fcis-25106.txt item: #395 of 872 id: fcis-25107 author: Chen, Xinfeng; Wu, Zhoujing title: High-speed Image Process in Pharmaceutical Bottle Production Basing OpenCV date: 2024 words: 2393 flesch: 36 summary: Future Work Despite the achievements of the real-time bottle defect detection system, there is still room for optimization and improvement. Additionally, exploring the application of new technologies such as deep learning in bottle defect detection may further improve the system’s performance and effectiveness. keywords: bottle; defect; detection; image; processing; system; time cache: fcis-25107.pdf plain text: fcis-25107.txt item: #396 of 872 id: fcis-25108 author: Yan, Fangxu; Wang, Jianhui; Li, Wei title: Research on the Application of Deep Learning in Natural Language Processing date: 2024 words: 2423 flesch: 48 summary: A basic neural network includes input layer, hidden layer and output layer. The basic structure of RNN includes input layer, hidden layer and output layer. keywords: input; language; layer; learning; network; text cache: fcis-25108.pdf plain text: fcis-25108.txt item: #397 of 872 id: fcis-25109 author: Zhao, Jingwei; Tao, Ye title: Application of Medical Records Management Based on Big Data Technology date: 2024 words: 2694 flesch: 33 summary: Improving Efficiency of Records Management Using big data technology, we can more easily store massive amounts of medical file data in a distributed manner, and we can integrate medical data from different sources and format them according to uniform standards. Unharmonized Data Standards and Norms Currently, there are major differences in the format, coding and storage standards for medical records data among different medical institutions, leading to difficulties in data sharing. keywords: data; information; management; medical; records; sharing; technology cache: fcis-25109.pdf plain text: fcis-25109.txt item: #398 of 872 id: fcis-25117 author: Chang, Junming; Ren, Qiong title: The Exploration of the Innovation Application Ability of Graduate Students Based on Multi-disciplinary Integration date: 2024 words: 1637 flesch: 19 summary: The integration has been the consensus of the educational circles, universities nowadays choose to lay emphasis on the research of innovative application ability driven by multi-disciplinary integration [1]. This research provides a new idea and method of innovation application ability based on multi-disciplinary integration. keywords: ability; application; integration; knowledge; training cache: fcis-25117.pdf plain text: fcis-25117.txt item: #399 of 872 id: fcis-25119 author: Xie, Jiaxuan; Zhou, Wenjie title: Solar Radiometer Efficiency Study Based on Particle Swarm Optimization Algorithms and Variable Parameter Goal Planning Design Models date: 2024 words: 3342 flesch: 47 summary: Based on the planning of establishing a heliostat field in a circular area, a shading efficiency model is established to study the optical efficiency of the heliostat field and its output efficiency under different sunlight angles and mirror parameters. [8] Schwarzbozl P, Schmitz M., Pitz-Paal R. Visual HFCAL - a software for layout and optimization of heliostat fields keywords: efficiency; field; heliostat; light; mirror; model; particle; power cache: fcis-25119.pdf plain text: fcis-25119.txt item: #400 of 872 id: fcis-25121 author: Wan, Yingdi title: Research on Dynasty Classification of Dunhuang Murals Based on Convolutional Neural Networks date: 2024 words: 3481 flesch: 57 summary: In 2013, a method was introduced based on the 71 essential contour structure of the mural images, which leads to high classification accuracy [2]. Due to the similarity of colors and painting styles, it is difficult to extract features in Dynasty classification. keywords: accuracy; classification; dynasties; dynasty; model; murals; network cache: fcis-25121.pdf plain text: fcis-25121.txt item: #401 of 872 id: fcis-25145 author: Yu, Yali title: Research and Analysis of Facial Expression Recognition Based on Deep Neural Networks date: 2024 words: 1710 flesch: 39 summary: Facial expressions are a non- verbal form of communication, but the amount of information conveyed through facial expressions is as high as 55%, indicating the importance of facial expression recognition in the process of communication. The second method is to extract facial expression features through deep neural networks, by constructing a neural network model with fewer parameters and smaller size, and training and predicting the model for facial expression recognition. keywords: convolution; expression; model; network; recognition cache: fcis-25145.pdf plain text: fcis-25145.txt item: #402 of 872 id: fcis-25702 author: Xu, Wei; Jin, Xiaodong title: Dynamic Layer Skipping for Large Language Models on Natural Language Understanding Tasks and Machine Translation Using Reinforcement Learning date: 2024 words: 7479 flesch: 62 summary: In detail, for Skip-decode, we set the maximum ratio of skipped layers to total layers at 90%, 70%, 50%, 30% , and 10% ; for the Yuan et al. The layer skipping ratio is computed by dividing the number of skipped layers by the total number of layers. keywords: adapter; arxiv; datasets; exiting; inference; language; layer; learning; llms; method; model; nlu; preprint; samples; skip; skipping; training; transformer cache: fcis-25702.pdf plain text: fcis-25702.txt item: #403 of 872 id: fcis-25709 author: Wang, Zishuo; Lai , Tianxiang; Wang, Yufeng; Gao, Xingquan title: 3D Point Cloud Semantic Segmentation based on Multi-scale Dense Nested Networks date: 2024 words: 6126 flesch: 55 summary: Compared with methods such as farthest point sampling[19], and inverse density sampling [20], MDNN uses random sampling operations to reduce the spatial resolution of point features, thereby improving computational efficiency and abstraction. Then, along the direction of the encoder path, the network gradually sparse the point cloud (where N is the number of points) in the order of (N→N/4→N/16→N/64→N/256→N/512), each level of MFFM learns the multi-scale of point features at multiple network levels, and gradually expands the receiving domain to obtain higher level of abstract semantic features. keywords: accuracy; aggregation; cloud; feature; fusion; information; layer; loss; mdnn; module; multi; network; point; scale; segmentation; semantic cache: fcis-25709.pdf plain text: fcis-25709.txt item: #404 of 872 id: fcis-25713 author: Huang, Huazheng; Huang, Guihua; Zhuo, Weijun; You, Minghui title: A Fast Face Changing Method Adaptable to Various Postures date: 2024 words: 3266 flesch: 51 summary: It can also ensure that user images with different poses and template images maintain high similarity with the user's face after face transformation without deformation. The user image upload submodule provides a user interface for users to upload or capture user source images, save them to the specified disk directory on the server, and save the path (URL) of the user source image in the server to the database, and store the source image URL in the Session buffer. keywords: coordinate; corner; face; image; source image; template; template image; user cache: fcis-25713.pdf plain text: fcis-25713.txt item: #405 of 872 id: fcis-25714 author: Chu, Yuhan title: A Communication Research on Reshaping the Content Ecosystem of New Media Platforms Based on AIGC Technology date: 2024 words: 2541 flesch: 24 summary: Such AIGC-based interactive applications not only increase user engagement and experiential satisfaction but also pave new avenues for the dissemination of media content. During the 20th National Congress of the Communist Party of China, People's Daily launched the New Thousand-Mile River Landscape multimedia product, showcasing the development achievements and struggles of the past decade in the new era using various new media technologies. keywords: aigc; communication; content; development; mainstream; media; technology cache: fcis-25714.pdf plain text: fcis-25714.txt item: #406 of 872 id: fcis-25715 author: Ren, Jiaqi title: Visualisation Design-Driven Research on Non-Heritage Dissemination and Digital Reproduction date: 2024 words: 3057 flesch: 29 summary: Some regions or groups are unable to introduce or reasonably and effectively use the Internet and digital technology due to backward infrastructure, poor economic conditions, and lagging scientific and technological development, thus restricting the digital dissemination of non-heritage culture; even in regions with access to the Internet, there are differences in the ability of different social groups to use the Internet, which makes it impossible for non- heritage to make good use of the resources of the Internet for dissemination; the digital technology The rapid development of digital technology requires users to have certain professional skills and knowledge, so it is difficult for non- heritage bearers to make use of modern scientific and technological means to present non-heritage content innovatively and disseminate it effectively due to factors such as their age, educational background and upbringing. Through these innovative ways, we can broaden the communication channels of non-heritage, enhance public awareness and interest in non-heritage, and promote the living inheritance and sustainable development of non-heritage culture. keywords: culture; design; digital; dissemination; heritage; non cache: fcis-25715.pdf plain text: fcis-25715.txt item: #407 of 872 id: fcis-25716 author: Wang, Xiuwei; Li , Biyuan title: DCSS-UNet: UNet based on State Space Model for Polyp Segmentation date: 2024 words: 4810 flesch: 58 summary: Machine learning (ML) algorithms, especially convolutional neural networks (CNNs), have shown promising results in medical image segmentation and have been applied to the detection and segmentation of polyps. We propose DCSS UNet, which is a potential application of the SSM-based model in medical image segmentation. keywords: attention; block; data; encoder; feature; figure; image; information; model; module; network; polyp; results; segmentation; sfa; unet cache: fcis-25716.pdf plain text: fcis-25716.txt item: #408 of 872 id: fcis-25717 author: Liu, Lijie title: Exploring Deep Learning Models for Lyric Generation and Addressing Biases in Word Embeddings date: 2024 words: 1265 flesch: 44 summary: Exploring Deep Learning Models for Lyric Generation and Addressing Biases in Word Embeddings Lijie Liu Rensselaer Polytechnic Institute Troy, Troy, New York, 12180 USA Abstract: The aim of this project is to explore the performance of different model architectures (such as RNN, LSTM, GRU) by generating lyrics using deep learning models, and to use the Word2Vec model for distributed semantic analysis to understand semantic phenomena and potential biases in word embedding models. 3. Results and Discussion Through training and comparing Vanilla RNN, LSTM, and GRU models, we found that LSTM and GRU exhibit better performance in processing long sequence data, specifically in terms of faster convergence speed and higher quality generated lyrics text. keywords: biases; model; word cache: fcis-25717.pdf plain text: fcis-25717.txt item: #409 of 872 id: fcis-25905 author: Zhang, Yue title: The Application of Data Security Protection in Enterprises date: 2024 words: 1938 flesch: 29 summary: Finally, through case studies, successful implementation effects of data security protection are demonstrated, highlighting the ongoing efforts and development directions for businesses in the field of data security. China Abstract: Data security protection is crucial in modern enterprises. keywords: data; enterprises; information; protection; security cache: fcis-25905.pdf plain text: fcis-25905.txt item: #410 of 872 id: fcis-25906 author: Yu, Yali; Huang, Zonghou; Liang, Jinchan title: A Review of Facial Micro Expression Recognition date: 2024 words: 2595 flesch: 45 summary: In addition, to avoid a single feature extraction method, deep neural network models or a combination of multiple models can be used to extract micro expression features, which can enhance the generalization ability and robustness of the network model in recognizing micro expressions. When collecting micro expression 47 samples, the emotions of the subjects need to remain neutral, and then micro expressions are spontaneously generated by environmental factors in specific scenes. keywords: dataset; expression; features; micro; recognition; research cache: fcis-25906.pdf plain text: fcis-25906.txt item: #411 of 872 id: fcis-25918 author: Chen, Rui title: Research on Indoor Automatic Path Planning Algorithm for Robots date: 2024 words: 6389 flesch: 38 summary: Deep reinforcement learning for indoor mobile robot path planning. These technologies encompass a wide range of disciplines, including navigation techniques, path planning algorithms, obstacle detection and avoidance strategies, and indoor environment modeling and map construction. keywords: algorithms; environments; navigation; path; path planning; planning; planning algorithms; research; robot; time cache: fcis-25918.pdf plain text: fcis-25918.txt item: #412 of 872 id: fcis-25923 author: Hui, Shuyue; Zhang, Yuanyuan title: A Virtual Reality Gearbox Experiment Platform Based on Hand Tracking and Natural Language Processing date: 2024 words: 5976 flesch: 38 summary: While traditional virtual experiment platforms have contributed to solving issues related to high equipment costs, 57 spatiotemporal limitations of resources, and operational safety, our VR platform shows significant advantages over these issues in detail interaction experience, personalized learning support, and immersive environment, compared to traditional approaches. Particularly in specialized fields such as electromechanical engineering in vocational education, medical laboratory, lathe operation, and maintenance of electrical equipment in coal mines, the application of virtual laboratory technology has become increasingly widespread. keywords: assembly; engineering; gearbox; hand; interaction; learning; module; observation; parts; platform; reality; students; technology; tracking; vol cache: fcis-25923.pdf plain text: fcis-25923.txt item: #413 of 872 id: fcis-25930 author: Yang , Yihe; Li, Xiaoming; Jin, Hongwei; Huang, Kun title: Advancing Structured Query Processing in Retrieval-Augmented Generation with Generative Semantic Integration date: 2024 words: 5407 flesch: 32 summary: Neural network architectures, such as sequence-to-sequence models, have been applied to translate natural language queries into structured query languages, facilitating more intuitive user interactions with databases[35][32]. In this paper, we introduce a novel method called Generative Semantic Integration (GSI), which advances structured query processing within RAG frameworks. keywords: data; document; generation; gsi; information; integration; language; models; query; rag; retrieval; university cache: fcis-25930.pdf plain text: fcis-25930.txt item: #414 of 872 id: fcis-25934 author: Li, Yongbo; Liu, Suping title: Research on an Enterprise Profiling Technique Based on Government Big Data date: 2024 words: 3188 flesch: 26 summary: In the pre-processing of enterprise data, it is mainly to clean the missing values and abnormal values of enterprise data, integrate, transform and standardize the data, and then divide and generate enterprise theme data according to functional departments, such as market supervision bureau, tax bureau, social security Bureau, tax bureau and water bureau. 2.2.2. Enterprise data are classified according to the theme of government data, mainly from the themes of economic construction, people's livelihood services, education technology, energy and environment. keywords: bureau; data; development; enterprise; enterprise profiling; government; information; profiling; technology cache: fcis-25934.pdf plain text: fcis-25934.txt item: #415 of 872 id: fcis-26107 author: Zhou, Zhanchong; Luo, Huailin; Zhang, Tao title: Research on Formation Reorganization Optimization and Trajectory Planning for Robotic Swan Light Performance on Water Surface date: 2024 words: 3822 flesch: 42 summary: Moreover, DMPC has high scalability and is adaptable for controlling the reorganization performance of different numbers of swan water surface robot formations. ̅ (3) In the formula: represents the distance from the initial position to the designated reorganization position for the swan surface robot; represents the total sum of the chordal distances; , , , are the initial position coordinates of the swan surface robot; , , , are the designated formation position coordinates of the swan surface robot; is the total number of swan surface robots participating in the group performance; represents the variance of the distances. 3.1.2. keywords: allocation; formation; performance; reorganization; robot; surface; swan; swan surface; water cache: fcis-26107.pdf plain text: fcis-26107.txt item: #416 of 872 id: fcis-26112 author: Lin, Zihao title: Transfer Learning with Pre-trained ResNet-50: Predicting SPX Option Prices date: 2024 words: 3948 flesch: 59 summary: The predicted option prices align well with the actual values, demonstrating the feasibility of applying pre-trained ResNet-50 on option price prediction. In the context of option price prediction, there are also several precedents for using machine learning methods. keywords: cnn; data; figure; learning; models; option; prediction; price; resnet-50; transfer cache: fcis-26112.pdf plain text: fcis-26112.txt item: #417 of 872 id: fcis-26326 author: Li , Wan; Huang, Sha; Wang, Hangfei; Chang, Chenyang title: Spatial Variance of Fusion and Physics-Aware for Single Image Dehazing date: 2024 words: 4574 flesch: 57 summary: Therefore, we utilize non-local image information over a larger spatial range for image enhancement. Multichannel Feature Extraction Traditional image dehazing methods often employ convolutional structures to extract local image information. keywords: attention; channel; dehazing; features; haze; image; information; model; transformer cache: fcis-26326.pdf plain text: fcis-26326.txt item: #418 of 872 id: fcis-26327 author: Li, Yichen; Zhang, Meina; Wang, Jiayu; Liu, Yuxuan; Xing, Yutong; Wang, Xinyuan title: Multi-Platform Electric Vehicle Detection System in Elevators date: 2024 words: 2410 flesch: 38 summary: The model is optimized to deliver high detection accuracy while being compact enough for deployment on edge devices, such as elevator monitoring systems. Conclusion The project effectively compresses the model size by adopting the lightweight version of YOLOv3—YOLOv3- Tiny—while maintaining high precision and recall rates, making it suitable for deployment on resource-limited edge devices, such as elevator monitoring systems. keywords: detection; electric; elevator; model; project; safety; system cache: fcis-26327.pdf plain text: fcis-26327.txt item: #419 of 872 id: fcis-26329 author: Ju, Mingjun; Li , Zhongmin; Wang, Jing; Guo, Xiaohui; Hu, Biao title: A Method of Dynamic Spatial Positioning of the Eyeball Based on Optic Disc Feature Following in Infants and Young Children date: 2024 words: 4997 flesch: 52 summary: Image size calibration and perspective distortion display 2.2. Especially in refractive surgery using laser means, accurate eye positioning can help doctors avoid damaging surrounding tissues during laser treatment keywords: center; centroid; disc; eyeball; fundus; image; method; optic; optic disc; point; positioning; rotation cache: fcis-26329.pdf plain text: fcis-26329.txt item: #420 of 872 id: fcis-26363 author: Shi, Yi title: Research on Grading Method for Jin Guan Apples based on Machine Vision date: 2024 words: 4494 flesch: 54 summary: Background Segmentation To facilitate the extraction of apple images, the inner walls of the dark chamber used for grading are painted black. To address the time-consuming and labor-intensive nature of apple grading, this paper focuses on the Jin-Guan apple variety and applies machine vision techniques to extract three key features: maximum transverse diameter, shape index, and surface color. keywords: apple; color; diameter; figure; grading; image; maximum; method; neural cache: fcis-26363.pdf plain text: fcis-26363.txt item: #421 of 872 id: fcis-26468 author: Huang, Jian; Zhuang, Manyi; Li, Bingzi; Chen, Xi; Wei , Lanzhen; Chen, Dongxiu title: Analysis and Monitoring Application of Medical Data for Chronic Diseases in Elderly Living Alone Based on Wearable Medical Sensor Wristbands date: 2024 words: 6947 flesch: 36 summary: In summary, this study combines methods such as literature review, user research, system design, data analysis, and experimental validation to achieve precise monitoring of chronic disease medical data in elderly individuals living alone, providing scientific evidence for health management. Data Collection Methods and Procedures This study employs multiple methods and procedures to collect chronic disease medical data for elderly individuals living alone. keywords: analysis; blood; bpm; data; disease; health; individuals; living; management; medical; monitoring; sensor; wristbands cache: fcis-26468.pdf plain text: fcis-26468.txt item: #422 of 872 id: fcis-26473 author: Wang, Yuxuan; Huang, Yi; Chen, Feng title: Optimisation of Spare Parts Quality Inspection Cost Based on Simulated Annealing and Genetic Algorithm date: 2024 words: 3715 flesch: 47 summary: For spare parts testing problem determines the existence of testing costs, so for spare parts mathematical and testing unit price multiplication should be divided by (1-a11) to obtain the final cost of testing for P2: (14) 3.4. Abstract: This paper provides an in-depth study on the impact of spare parts quality inspection on production costs in the electronics industry. keywords: cost; inspection; parts; process; product; quality; rate; testing cache: fcis-26473.pdf plain text: fcis-26473.txt item: #423 of 872 id: fcis-26478 author: Wang, Jiaying; Chen, Yinxing; Wu, Weijie title: A Survey on Multimodal Multiobjective Optimization Algorithm date: 2024 words: 3463 flesch: 44 summary: In order to visually demonstrate the characteristics of multimodal multi-objective optimization problems, Figure 1 provides a schematic diagram of the multimodal multi- objective optimization problem. This article will provide a detailed introduction to the relevant concepts, research progress, testing functions, and evaluation indicators of multimodal multi-objective optimization algorithms. keywords: algorithm; decision; multimodal; objective; optimization; pareto; problems; solution; space cache: fcis-26478.pdf plain text: fcis-26478.txt item: #424 of 872 id: fcis-26529 author: Ye, Xinbin; Peng, Haojun; Liao, Hanwei title: Research and Practice of IoT Technology based on Smart Campus date: 2024 words: 2763 flesch: 42 summary: This study highlights the unique advantages and broad application prospects of student arrival IoT management system integrating big data under the background of smart campus. b 157269062@qq.com Abstract: This paper designs and implements an Internet of Things (IoT) student arrival management system based on smart campus, and uses big data technology to solve the problems of information lag and inaccuracy in traditional management mode. keywords: arrival; campus; data; management; school; students; system; technology; time cache: fcis-26529.pdf plain text: fcis-26529.txt item: #425 of 872 id: fcis-26581 author: Shi, Xinlei title: Exploring the Influence from London Development on London Underground Mobility Through Network Analysis date: 2024 words: 4082 flesch: 50 summary: This study investigates the commuting patterns of London citizens in the subway and explores the impact of human activities on the importance of network nodes in subway stations. Analyzed the degree centrality, betweenness centrality, and closeness centrality of the London underground transportation network. keywords: betweenness; centrality; closeness; degree; efficiency; london; network; nodes cache: fcis-26581.pdf plain text: fcis-26581.txt item: #426 of 872 id: fcis-26582 author: Chen, Ling title: Research on Code Generation Technology based on LLM Pre-training date: 2024 words: 5006 flesch: 53 summary: The above research demonstrates a trend to improve the performance of code generation models by improving model architecture, introducing task-specific pre-training, and combining different learning methods. In recent years, the development of LLM technology has attracted extensive attention from industry and academia, and since the early representative language model GPT-3 was proposed in July 2020, code models have been emerging due to their excellent natural language processing task processing capabilities, question answering and code capabilities. keywords: arxiv; code; code generation; data; generation; language; model; pre; preprint; programming; research; tasks cache: fcis-26582.pdf plain text: fcis-26582.txt item: #427 of 872 id: fcis-26660 author: Wang, Shimeng; Zhang, Qipeng; Tian, Zhe; Zhao, Meng title: Research on High Frequency Usage Scenarios of Touch Interactive in Dynamic Scenarios date: 2024 words: 2097 flesch: 41 summary: Research result on relevant stand Research on Scenario Library Navigation Air Conditioning Music Phone Radio Setting ADAS E-NCAP 2026 Road map √ √ NHTSA-2010-0053 √ √ √ √ √ √ √ T/CSAE 334-2023 √ √ √ √ √ √ C-ICAP √ √ An Evaluation Method for HMl Scenarios in Intelligent Connected Vehicles √ √ √ √ √ √ 4.2. Next, we will carry out user research on a sample size of over 100 users through survey questionnaires. keywords: control; driving; interaction; research; scenarios; touch cache: fcis-26660.pdf plain text: fcis-26660.txt item: #428 of 872 id: fcis-26688 author: Chen, Yeming title: Research on Assembly and Detection Optimization Based on Multi-objective Decision Model and Genetic Algorithm date: 2024 words: 2738 flesch: 49 summary: (2) Binomial distributions briefly describe the sampling process The number of defective products obeys the binomial distribution , , where is the total number of samples; is the nominal defective rate. The probabilistic mass function for the number of defects is: 1 (3) Where is the number of defective products detected. keywords: cost; distribution; parts; products; rate cache: fcis-26688.pdf plain text: fcis-26688.txt item: #429 of 872 id: fcis-26720 author: Huang, Rongzhao; Chen, Ang; Bai , Menglin; Bian, Bawangdui title: Tibetan Speech Emotion Recognition based on Capsule Network and Spatiotemporal Features date: 2024 words: 4514 flesch: 53 summary: Although deep learning has made remarkable progress in the field of speech emotion recognition, the research of Tibetan speech emotion recognition is still relatively lagging behind. The speech emotion recognition task includes many key steps, the core parts of which are: building a speech emotion corpus, extracting speech emotion features, model training and evaluation. keywords: corpus; emotion; features; model; network; paper; recognition; speech; tbsec001; tibetan; training cache: fcis-26720.pdf plain text: fcis-26720.txt item: #430 of 872 id: fcis-26721 author: Peng, Xianghua; Pan, Xianmin title: Application Research of Neural Network in the Tensile Constitutive Relationship of Carbon Steel date: 2024 words: 3212 flesch: 46 summary: In this paper, a constitutive model of carbon steel based on neural network is established by using the high precision nonlinear fitting ability and strong generalization ability of neural network, reflect its different stages of mechanical properties. Carbon steel has many excellent physical and chemical properties and is widely used in fields such as construction, transportation, energy, packaging, home appliances, and industry. keywords: carbon; carbon steel; figure; model; network; neural; relationship; steel; stress; tensile cache: fcis-26721.pdf plain text: fcis-26721.txt item: #431 of 872 id: fcis-26722 author: Zhang, Dongpo; She, Zhiyong; Zhang, Jiaqi title: Research on Particle Swarm Image Threshold Segmentation Method Based on Rough Set date: 2024 words: 4547 flesch: 65 summary: Variations of various variables in image segmentation Th (Segmentation threshold)  (Classification error) ( )B O (Dependency) 25 0.4754 0.0048 37 0.4702 0.0037 43 0.4765 0.0021 56 0.4518 0.0065 76 0.4534 0.0015 139 0.4831 0.0061 152 0.4989 0.0025 195 0.4624 0.0036 214 0.4812 0.0027 Only representative values were selected throughout the algorithm. Image segmentation plays an important role in image processing. keywords: algorithm; dependency; image; segmentation; set; threshold; vprs cache: fcis-26722.pdf plain text: fcis-26722.txt item: #432 of 872 id: fcis-26723 author: Zhang, Daohai; Zhang, Shang title: Prediction of Final Grade of Advanced Mathematics based on BP Neural Network date: 2024 words: 3971 flesch: 50 summary: Student achievement prediction, also known as student academic performance prediction, is one of the important research issues in education data[3]. It can be seen from the figure that the accuracy of prediction results of BP God network performance prediction model is 69.3%. keywords: data; layer; learning; network; neural; output; prediction; students cache: fcis-26723.pdf plain text: fcis-26723.txt item: #433 of 872 id: fcis-26832 author: He, Huiqian; Chen, Wenxiu; He, Yuan; Mo, Yongyu; Du, Shuhua; Yao, Yilin; Zhu , Yuwan; Li, Songyuan; Li, Xiaotong; Chen, Aixia title: Research on the Information Interaction Design of Special Agricultural Products Apps from the Perspective of Rural Revitalization date: 2024 words: 3572 flesch: 30 summary: Therefore, this paper, from the perspective of information interaction design, identifies pain points in existing app designs through literature review and case analysis, and explores methods to optimize the user experience of agricultural product apps. For agricultural product apps, information interaction design can employ intuitive charts, images, and other formats to present product information, allowing users to quickly grasp the characteristics and advantages of the products. keywords: agricultural; app; design; development; experience; information; interaction; product; research; revitalization; user cache: fcis-26832.pdf plain text: fcis-26832.txt item: #434 of 872 id: fcis-26857 author: Zhang, Yifan; Zhang, Ruiwei; Zhang, Shihan; Jia, Zhifu title: Precipitation Prediction in Suqian City, Jiangsu Province of China Using LSTM Based on Grey Wolf Optimizer Algorithm date: 2024 words: 7163 flesch: 50 summary: Firstly, we collected five years of precipitation data to ensure a solid foundation for model training. In this context, precipitation prediction has become particularly important. keywords: city; data; grey; gwo; lstm; lstm model; memory; model; network; precipitation; prediction; season; suqian; term; time cache: fcis-26857.pdf plain text: fcis-26857.txt item: #435 of 872 id: fcis-26982 author: Zhao, Yang; Ding, Jianwei title: Experimental Design of Face Image Restoration Teaching date: 2024 words: 2077 flesch: 42 summary: Through practical operation, the students' enthusiasm for research in the field of image restoration is cultivated. Through practical operation of pycharm software, functions such as image reading, evaluation of restoration results and visualization of results were realized, which stimulated students' interest in image restoration, improved their scientific research quality and practical ability, and laid a solid foundation for future scientific research and practical work. keywords: image; model; network; repair; restoration; structure; students cache: fcis-26982.pdf plain text: fcis-26982.txt item: #436 of 872 id: fcis-26988 author: Yan, Shaobo; Xu, Danyang title: Portable Buzzer Circuit Design for Reform of Electronic Technology Experiments date: 2024 words: 1954 flesch: 37 summary: Students are provided with comprehensive experimental equipment and materials, the experiment center has specially set up three laboratories for electronic technology experiments for teaching purposes, each laboratory is equipped with 50 workstations, providing each student with an experimental workstation and equipment, and simulation software such as Multisim and QuartusII are pre-installed on the experimental computers, while each student's seat is equipped with a component box, breadboard, toolbox, and other tools. 4. Conclusion Through reforming and practicing electronic technology experiments with design projects as the goal, students have essentially gone through processes such as familiarization with experimental instruments, analysis and design of circuit principles, component selection, circuit simulation and testing, and breadboard circuit assembly. keywords: buzzer; circuit; design; experiment; students cache: fcis-26988.pdf plain text: fcis-26988.txt item: #437 of 872 id: fcis-2707 author: Han, Suyu title: Hybrid Attention Fusion in Dense Crowd Counting date: 2022 words: 2371 flesch: 55 summary: [5] considers the density of different regions in an image varies greatly, leading to heterogeneous counting performance, and therefore proposes density attention networks to provide multi-scale attention masks for convolutional extraction units. Hybrid attention network based on progressive embedding scale-context for crowd counting[J]. keywords: attention; computer; conference; counting; crowd; density; map; vision cache: fcis-2707.pdf plain text: fcis-2707.txt item: #438 of 872 id: fcis-2708 author: Huang, Junrong title: Research on the Application of Artificial Intelligence in Image and Text Database Retrieval date: 2022 words: 2327 flesch: 44 summary: China Abstract: In the graphic database, the difficulty of query processing lies in how to query the contents of various data, that is, content-based retrieval, which is an effective means and an important technology to realize multimedia data retrieval. In graphic database, the difficulty of query processing lies in how to query the content based on unformatted data, that is, content-based retrieval, which is an effective means and an important technology to realize multimedia data retrieval. keywords: data; database; retrieval; technology cache: fcis-2708.pdf plain text: fcis-2708.txt item: #439 of 872 id: fcis-27147 author: Xu, Gaofeng; Lu, Xinchen title: Research on Predicting Stock Market Profitability Changes Based on Machine Learning date: 2024 words: 3010 flesch: 41 summary: The development of artificial intelligence technology has played a crucial role in driving stock model prediction. With the development and gradual maturity of machine learning technology, machine learning models are used for efficient and accurate analysis of massive data in the stock market, thereby achieving data mining in the stock market, analyzing changes in stock returns, and predicting them to improve investor returns. keywords: data; index; investment; learning; machine; market; model; prediction; stock cache: fcis-27147.pdf plain text: fcis-27147.txt item: #440 of 872 id: fcis-27148 author: Zhao , Chenchen title: API Common Security Threats and Security Protection Strategies date: 2024 words: 2417 flesch: 39 summary: Unauthorized Access In the field of API security, ultra vires access is a key issue, which is rooted in the diversity of API authentication logic and incomplete implementation Therefore, the reasonable application of OAuth, JWT and other authentication mechanisms, and the implementation of fine-grained rights management is an effective strategy to enhance API security and protect data and system integrity. keywords: access; api; apis; authentication; data; figure; protection; security cache: fcis-27148.pdf plain text: fcis-27148.txt item: #441 of 872 id: fcis-27189 author: Chen, Huangkun; Sun, Liangxu title: The Intelligent Decision-making and Collaboration Mechanism Design of the Soccer Robot System date: 2024 words: 3774 flesch: 46 summary: This model has been widely applied in soccer robot systems. Implementation solutions for robot soccer include: robot soccer simulation competitions, vision-based remote- controlled robot soccer systems, vision-based robot soccer systems, and fully autonomous robot soccer systems[5]. keywords: angle; ball; car; control; decision; making; robot; soccer; subsystem cache: fcis-27189.pdf plain text: fcis-27189.txt item: #442 of 872 id: fcis-27197 author: Song, Yingjie title: Improving the Performance and Efficiency of Convolutional Neural Networks (CNNs) on Image Classification Tasks via Fixed-Point Quantization and Structured Pruning date: 2024 words: 2938 flesch: 40 summary: The metrics of model accuracy, inference speed, model size, and memory consumption after quantization are evaluated, focusing on the trade-off between accuracy loss and computational complexity. A comprehensive survey on model quantization for deep neural networks in image classification. keywords: accuracy; inference; model; pruning; quantization; speed cache: fcis-27197.pdf plain text: fcis-27197.txt item: #443 of 872 id: fcis-27233 author: Zhai, Bo; Zhu, Hanxue; Wan, Hongzhuang title: Research on Crop Planting based on Linear Programming and Multiple Regression Functions date: 2024 words: 3686 flesch: 49 summary: In the study, we consider a variety of factors such as crop planting seasons, plot types, and potential planting risks. Abstract: The purpose of this paper is to explore how to optimize crop planting strategies through linear programming and multiple regression functions to help rural revitalization and agricultural modernization. keywords: correlation; crop; planting; price; sales; sales volume; season; volume cache: fcis-27233.pdf plain text: fcis-27233.txt item: #444 of 872 id: fcis-27234 author: Yu, Ziyang; Yu, Xinpeng; Liu, Yinuo; Li, Yue; Zeng, Yuyan; Liu , Yanqing title: Prediction of Sunspot Activity Based on Differential Evolution Algorithm and BP Neural Network Model date: 2024 words: 3720 flesch: 52 summary: In addition, the reliability of the time series prediction model based on particle swarm optimization BP neural network is verified by comparing it with BP neural network model. Based on adaptive multivariate nonlinear regression -BP neural network model for solar activity prediction, first establish the relationship between time and the number of sunspots model, and then based on the differential evolution algorithm model for solving, and then use the differential evolution algorithm model and BP neural network model for mixed model to solve, calculate the maximum for back generation, to achieve the next cycle prediction. keywords: correlation; data; model; network; neural; number; prediction cache: fcis-27234.pdf plain text: fcis-27234.txt item: #445 of 872 id: fcis-27338 author: Yang, Nirunze; Wang, Manna; Zhu, Yongjian title: Research on Methods for Developing Software Identification Codes in Automotive Software Update Management Regulations date: 2024 words: 3647 flesch: 41 summary: The UN R156 regulation requires automobile manufacturers and suppliers to establish a sound software update management system to ensure the safe and reliable update of vehicle software. Introduction With the in-depth development of automotive electronics, there are more and more on-board ECUs (Electronic Control units) that support software updates. keywords: code; identification; information; requirements; rxswin; software; software update; type; update; vehicle cache: fcis-27338.pdf plain text: fcis-27338.txt item: #446 of 872 id: fcis-27339 author: Wang, Yuzhe; Mu, Zhapa; Zhu , Yongjian; Wang, Manna; Shao, Xuebin title: Research on Regulations on Software Update of Intelligent Connected Vehicles date: 2024 words: 2962 flesch: 33 summary: The Development of Automotive OTAs The development of automotive over-the-air (OTA) technology is a revolutionary advancement in the field of intelligent and connected vehicles, which enables automakers to remotely update and manage vehicle software and firmware over wireless networks. However, with the spread of software update technology, car manufacturers can easily bypass the existing automotive product management system and arbitrarily change key parameters such as vehicle safety, emissions, and energy consumption, thereby obtaining undue benefits. keywords: automotive; management; safety; software; technology; update; vehicles cache: fcis-27339.pdf plain text: fcis-27339.txt item: #447 of 872 id: fcis-27414 author: Yu, Ruofeng; Wu, Yating; Yu, Ruoyu title: Research on CT System Image based on Back Projection Reconstruction Model date: 2024 words: 2513 flesch: 54 summary: The problem of projection image reconstruction can be solved according to the following process: firstly, the projection must be collected under different angles. However, it is challenging to identify a method of projection reconstruction based on line integrals. keywords: filter; function; image; projection; reconstruction cache: fcis-27414.pdf plain text: fcis-27414.txt item: #448 of 872 id: fcis-27435 author: Li, Yanping; Yang, Qingjun; Lai, Zhiyun; Qian, Yu title: Benchmark Dataset Applied to Quantitative Precipitation Estimation and Forecasting of Qinghai date: 2024 words: 3258 flesch: 46 summary: Short- duration heavy precipitation is one of the meteorological disaster that needs to be prevented. The dataset was divided into two subsets: radar echo extrapolation dataset and quantitative precipitation estimation dataset. keywords: dataset; duration; echo; meteorological; observation; precipitation; qinghai; radar; weather cache: fcis-27435.pdf plain text: fcis-27435.txt item: #449 of 872 id: fcis-27462 author: Li, Xiaoling; Hu, Guoqiang title: Design and Implementation of an Electronic Journal Resource Recommendation System Integrating User Profile and Knowledge Graph date: 2024 words: 3336 flesch: 37 summary: Regarding the analysis of existing user profiling models, the acquisition of user data generally starts from four dimensions: natural attributes, user preference attributes, interaction behavior attributes, and social behavior attributes. Building accurate user profiles requires tagging and vectorizing user data to provide computable numerical 76 information for subsequent data analysis. keywords: data; graph; information; journal; knowledge; management; module; recommendation; system; user cache: fcis-27462.pdf plain text: fcis-27462.txt item: #450 of 872 id: fcis-27463 author: Liu, Zhiwei; Liu, Di; Liu, Song title: Optimization of Unmanned Vehicle Delivery Routes Considering Charging and Time Windows date: 2024 words: 5370 flesch: 55 summary: Model parameters and variables Parameter Description L Customer Point Collection S Set of unmanned vehicles, subscript denoted as s U Charging station collection Z Distribution center, subscript denoted as z N Set of all points, subscript denoted as n , N L U Z   C The cost of unmanned vehicle delivery per unit distance ijd Distance from point i to point j , ,i j N ib Customer i 's demand for goods, i L B Maximum load capacity of unmanned vehicle e nsw Remaining power when unmanned vehicle s reaches point n l nsw The remaining power when the unmanned vehicle s leaves point n W Battery capacity of unmanned vehicle i Earliest service time of customer i time window, i L i Latest service time of customer i time window, i L C Waiting costs incurred by early arrival of unmanned vehicles C Penalty costs incurred by unmanned vehicles arriving later than the time window e it Time when the unmanned vehicle arrives at point i , i N l it keywords: center; charging; delivery; distribution; point; time; vehicle cache: fcis-27463.pdf plain text: fcis-27463.txt item: #451 of 872 id: fcis-27586 author: Zhao, Zikai; Zheng, Yanting; Guo, Qingxiang; Li, Mengqi; Li, Lujiang; Wang, Limin title: Trajectory Calculation for Dummy Part Trajectory in Vehicle Collision Tests date: 2024 words: 3404 flesch: 45 summary: By adhering to standardized methods and clear protocols for defining rotations, researchers can streamline their analytical processes, minimize errors, and enhance the accuracy of their findings. Benchmarking involves comparing the outputs of virtual crash simulations with real- world data obtained from physical crash tests to ensure that the virtual models accurately capture the dynamics of a crash scenario. keywords: coordinate; dummy; head; method; rotation; sin cache: fcis-27586.pdf plain text: fcis-27586.txt item: #452 of 872 id: fcis-27588 author: Liu, Yang; Hou, Zhesheng; Bai, Zhengxiao title: Research and Development of Powertrain of Bionic Mobile Rechargeable Material Truck date: 2024 words: 2623 flesch: 58 summary: Power part of track chassis 1. Crawler Chassis 3D Modeling The crawler chassis is designed to adapt to the complex forest terrain, and its structure mainly includes dual brushless DC motors, speed reducers, drive wheels, support wheels, guide wheels and tracks. keywords: chassis; corn; driving; force; speed; track; vehicle; wheel cache: fcis-27588.pdf plain text: fcis-27588.txt item: #453 of 872 id: fcis-27603 author: Ju, Yongsheng; Feng, Yanjun; Cao, Zhe title: Numerical Simulation Analysis of Loess Slope Stability under the action of Power Tower foundations date: 2024 words: 2110 flesch: 62 summary: This study is of great significance to the safety construction of power tower and the improvement of loess slope stability. According to the characteristics of the influence of loess slope settlement on stability, it is determined that the upper surface of the model is a free surface, which only needs to be constrained on both sides of the X and Y directions and below the Z direction. keywords: foundation; loess; scheme; slope; stability; tower cache: fcis-27603.pdf plain text: fcis-27603.txt item: #454 of 872 id: fcis-27905 author: Lv , Tianci; Cheng, Mengyuan title: Flexible Local Differential Privacy Mechanism for Collecting Location Data date: 2024 words: 2643 flesch: 49 summary: To address this, scholars have proposed methods such as Differential Privacy (DP) and Local Differential Privacy (LDP) to protect location privacy. Therefore, collecting location data while protecting user privacy has become a significant challenge. keywords: data; location; output; perturbation; privacy; probability; range cache: fcis-27905.pdf plain text: fcis-27905.txt item: #455 of 872 id: fcis-27931 author: Wang, Zhibin; Zhu, Jianjun title: Solving Multi-robot Task Assignment Problem based on Improved Genetic Algorithm date: 2024 words: 3463 flesch: 52 summary: Through experimental comparison, the algorithm in this paper has improved the balance of task allocation and solution efficiency, can adapt to the task allocation of warehousing environments with different degrees of task numbers, and has obvious advantages in solving multi-robot task allocation. [3]proposed a warehouse robot task allocation algorithm based on the immune ant colony optimization algorithm, with the robot's total path as the goal, to achieve multi-objective task allocation; Zhou Hang et al.[4] proposed a hybrid genetic taboo search algorithm, with the robot delivery cost as the goal, to improve the overall operation efficiency of the warehouse; Deng Fuqin et al. keywords: algorithm; allocation; crossover; improve; point; population; robot; task cache: fcis-27931.pdf plain text: fcis-27931.txt item: #456 of 872 id: fcis-28010 author: La, Yuxian; Xu, Guoyuan; Chang, Yanping; Yuan, Zhifu; Zhang, Shaochen title: Malfunction and Emergency Response of Qinghai Meteorological HD Video Consultation System date: 2024 words: 3184 flesch: 44 summary: Implementation of Fault Handling and Rapid Emergency Response Due to the multiple factors affecting the operation of the provincial consultation system, the types of faults involved are complex, mainly including 9 major subsystem faults such as video network, MCU server, video and audio processing terminal, and display. The system has made a good design in emergency plan, fundamentally solving the problem of 3 major faults in video network, MCU server, and video terminal, realizing automatic routing and backup switching of the system, ensuring that the main equipment and network of the system can quickly respond to emergencies, and ensuring stable and reliable system operation. keywords: backup; conference; emergency; meteorological; network; system; terminal; video cache: fcis-28010.pdf plain text: fcis-28010.txt item: #457 of 872 id: fcis-28019 author: Yue, Zhen; Wang, Haiyang title: Parkinson's Disease Speech Classification Using 1D Convolutional Neural Networks date: 2024 words: 1407 flesch: 51 summary: Keywords: Parkinson Disease; Speech Features; Convolutional Neural Networks. [5] Bagging algorithm 98.28% Haq et al. (2018) keywords: dataset; disease; parkinson; speech cache: fcis-28019.pdf plain text: fcis-28019.txt item: #458 of 872 id: fcis-28030 author: Meng, Hao; Tan, Jieqing title: An Improved Algorithm for Small Target Detection based on YOLO date: 2024 words: 2758 flesch: 51 summary: Small target detection is an important branch of target detection, which mainly focuses on small targets in images, such as pedestrians in video surveillance and small lesions in medical images. However, YOLO algorithm[1-3], with its powerful feature[4] extraction capability and global optimization strategy[5], has shown excellent performance in small target detection. keywords: algorithm; detection; feature; model; module; performance; small; target; yolo cache: fcis-28030.pdf plain text: fcis-28030.txt item: #459 of 872 id: fcis-28118 author: Yang, Shiwei; Chen, Xiaozhou title: Prediction of Protein Secondary Structure Using a Hybrid Convolutional Blocks with GRU Units date: 2024 words: 5749 flesch: 52 summary: This enables the extraction of protein sequence information more completely. Different from previous convolutional neural networks architectures, in this study, we used a mixture of two convolutional blocks of different scales combined with GRUs for sequence labeling for protein secondary structure prediction. keywords: accuracy; amino; data; function; information; layer; learning; model; network; prediction; protein; rate; sequence; structure cache: fcis-28118.pdf plain text: fcis-28118.txt item: #460 of 872 id: fcis-28151 author: Zhang, Yichi; Bu, Fanliang title: Design and Implementation of Decision Support System for Airport Emergency Disposal date: 2024 words: 5725 flesch: 45 summary: Design and implement-ation of emergency decision support system ba-sed on CBR and RBR, Software Guide, 2019,18(02):55-59. The backend management subsystem includes case management, user management, and decision-support engine management. keywords: case; decision; decision support; diagram; emergency; information; management; reasoning; results; subsystem; support; system; user cache: fcis-28151.pdf plain text: fcis-28151.txt item: #461 of 872 id: fcis-28393 author: Yu, Feifei title: Prediction of Runoff in Huayuankou of the Yellow River based on Autoformer-LSTM date: 2024 words: 3688 flesch: 49 summary: The measured data of Huayuankou hydrological station on the Yellow River from January 1,2002 to December 31,2022 were selected to carry out simulation verification, and the effectiveness of various runoff prediction models was compared and analyzed by ablation method. In order to improve the accuracy of runoff prediction, domestic and foreign scholars have proposed a variety of prediction models, which can be broadly categorized into process-driven and data-driven models based on their construction bases and core logic[2]. keywords: autoformer; correlation; data; lstm; model; prediction; runoff; series; t t; time cache: fcis-28393.pdf plain text: fcis-28393.txt item: #462 of 872 id: fcis-28490 author: Miao, Haoxu title: Crop Planting Strategy based on Greedy Algorithm and Monte Carlo Simulation date: 2024 words: 2513 flesch: 63 summary: (2) Determine the model function Based on the above conditions, the objective function is established as follows: ∑ ∑ ∑ ∗ ∗ ∗ ∗ ∑ ∑ ∑ ∗ ∗ ∗ ∗ ∗ ∑ ∑ ∑ ∗ ∗ ∗ ∗ ∗ ∑ ∑ ∑ ∗ ∗ ∗ ∗ ∗ ∑ , ∈ 1,2, … ,41 , ∈ 1,2, … ,82 ∗ ∑ 0 All leguminous cropsi,x ∈ 1,2,3,4,5 . 0 , ∈ 1,2, … ,15 , ∈ 1,2, … ,26 , ∈ 0,1, … ,7 0 , 16, ∈ 27,28, … ,34 , ∈ 0,1, … ,7 0 , ∈ 17,18,… ,34 , ∈ 27,28,… ,54 ∪ 79,80,81,82 , ∈ 0,1, … ,7 0 , ∈ 35,36,37 , ∈ 55,56,… ,62 , ∈ 0,1, … ,7 0 , ∈ 38,39,40,41 , ∈ 63,64,… ,78 , ∈ 0,1, … ,7 0 , ∗ , ∈ 1,2, … ,34 , ∈ 0,1, … ,7 (5) 4.3. Based on this condition, the equation is established as follows: ∑ ∑ ∑ ∗ ∗ ∗ ∗ ∗ (2) takes values from -10% to 10% (except for the two types of greenhouses). keywords: crops; land; planting; ∗ ∗ cache: fcis-28490.pdf plain text: fcis-28490.txt item: #463 of 872 id: fcis-28492 author: Wei, Yifan; Ji, Mingye; Wang, Cuicui title: An Exploration of Crop Planting Based on Simulated Annealing Algorithm and Mixed Integer Linear Programming date: 2024 words: 3530 flesch: 60 summary: Then, Pearson correlation coefficient and cross-elasticity coefficient are introduced to analyze the correlation between variables such as crop sales price and planting cost, and constrained optimization. In addition, through the application of Pearson's correlation coefficient and cross-elasticity coefficient, the relationship between crop sales price and planting cost was analyzed, and 64 alternative and complementary crops were identified to further optimize planting decisions. keywords: correlation; crop; planting; price; sales; year cache: fcis-28492.pdf plain text: fcis-28492.txt item: #464 of 872 id: fcis-28493 author: Li, Hongyi; Zhu, Jianjun title: Research on Robotic Arm Grasping Algorithm Based on an Enhanced Edge Network date: 2024 words: 3989 flesch: 50 summary: To effectively utilize point cloud data for model training, key features such as point cloud coordinates and normal information were first extracted from the .npz files. In contrast, point cloud data directly captures the position and shape of objects in three-dimensional space, offering rich depth information. keywords: cloud; data; detection; feature; grasp; grasping; model; module; network; point cache: fcis-28493.pdf plain text: fcis-28493.txt item: #465 of 872 id: fcis-28505 author: Wei, Yilei title: Bayesian Network-based Inferential Analysis of Xigou Reservoir Overtopping Accident date: 2024 words: 5174 flesch: 49 summary: Results of conditional probability calculations for the node “Monitoring System” Monitoring System (F2) expert opinion calculation result M1 M2 M3 M4 M5 Normal Monitoring (F21) (0.15,0.85) (0.3,0.7) (0.25,0.75) (0.25,0.75) (0.2,0.8) (0.23,0.77) Erroneous Monitoring (F22) (0.75,0.25) (0.6,0.4) (0.7,0.3) (0.75,0.25) (0.8,0.2) (0.72,0.28) 75 4. Results and Analysis After constructing the Bayesian network structure and determining the conditional probabilities of the nodes of “Xigou Reservoir Overtopping Accident”, we start to construct the complete Bayesian network of “Xigou Reservoir Overtopping Accident” scenario. As shown in Fig, the inference calculates the state probability of each node variable in the Bayesian network of “Xigou Reservoir Overtopping Accident”. keywords: accident; bayesian; dam; emergency; level; maintenance; network; probability; reservoir; scenario; state; status; water; xigou cache: fcis-28505.pdf plain text: fcis-28505.txt item: #466 of 872 id: fcis-28514 author: Tan, Yingying; Song, Jinpeng; Chu, Chen title: Detection of Small Object based on Improved-YOLOv8 date: 2024 words: 4575 flesch: 54 summary: For example, in terms of data preprocessing technology, data enhancement strategies such as Mosaic [1] and Copy-Pasting [2] are applied to dataset to improve the proportion of small objects in the image, so as to enhance the learning ability of the algorithm model for small object features. In shallow layers, feature maps contain various scale target information, while feature maps loses a lot of small object feature in deep layers. keywords: detection; feature; information; maps; model; module; network; object; small; transform; wavelet cache: fcis-28514.pdf plain text: fcis-28514.txt item: #467 of 872 id: fcis-28515 author: Xie, Nanmei; Xu, Wenjun title: Analysis of the Evaluation Data of College Classroom Teaching Quality based on Fuzzy Mathematics Model date: 2024 words: 4200 flesch: 52 summary: Analysis form of 9 evaluation experts Evaluation expert Number of evaluation sections Average section Quantification of professional title Expert 002 333 2.55 0.6140 Expert 003 417 1.95 0.5719 Expert 005 460 2.73 0.5476 Expert 006 490 1.95 0.5595 Expert 012 90 2.60 0.5845 Expert 025 675 2.51 0.5474 Expert 027 394 2.25 0.5371 Expert 028 787 2.74 0.5480 Table 10. 9 expert evaluation conclusions Evaluation expert Evaluation conclusion Expert 002 have many times of class evaluation, rich experience in class evaluation and high professional title level Expert 003 have a lot of class evaluation times, few class evaluation sessions, and average professional titles Expert 005 have more times of class evaluation, more class evaluation sessions, and strong reserves of professional knowledge Expert 006 have more class evaluation times, fewer class evaluation sessions, and average professional title level Expert 012 have few times of class evaluation, many class evaluation sessions, and strong professional knowledge reserve Expert 025 have many times of class evaluation, rich experience in class evaluation and strong reserves of professional knowledge Expert 027 have moderate times of class evaluation, rich experience in class evaluation, and low professional title level Expert 028 have a lot of times to evaluate the course, a lot of times to evaluate the course, and a strong reserve of professional knowledge 94 From the ranking of experts, it can be found that the more the number of evaluation sections, the higher the ranking of experts; The number of sections evaluated by expert 001 and expert 026 is the same, both of which are 51. For question 3: the grey correlation model is established according to the factors that affect the professionalism and objectivity of evaluation experts, such as teachers' professional titles, the number of evaluation sessions and the average number of sessions. keywords: 0.9126; class; classroom; course; data; evaluation; expert; quality; teaching cache: fcis-28515.pdf plain text: fcis-28515.txt item: #468 of 872 id: fcis-28660 author: Bai, Xue; Wei, Gao; Ye, Tao title: Analysis and Optimization Scheme of the Effectiveness of Word2vec in Intelligent Recommendation of Traditional Chinese Medicine Folk Prescriptions date: 2024 words: 5162 flesch: 48 summary: 4. Conclusion This paper mainly introduces the calculation method of word2vec, and the operation steps of the model mainly include three parts: the feature acquisition of user input text, the feature learning of user folk formula, and the generation of recommendation result. Display feedback refers to user information, reviews, etc. keywords: folk; information; input; method; model; network; neural; prescription; recommendation; similarity; text; user; word cache: fcis-28660.pdf plain text: fcis-28660.txt item: #469 of 872 id: fcis-28761 author: Liu, Jiajia; Huang, Chidong title: Multi-Scale Adaptive Road Extraction Network for High-Resolution Remote Sensing Images date: 2024 words: 4106 flesch: 47 summary: The comparison of road extraction results demonstrates that MARENet performs well in handling complex road scenarios, adapting to different road conditions, and addressing challenges caused by varying road orientations and widths. Abstract: Road extraction from high-resolution remote sensing images faces challenges such as discontinuities caused by occlusions from trees and buildings, as well as computational complexity arising from varying road orientations and widths. keywords: apc; attention; extraction; fat; feature; images; module; network; road; segmentation; sensing cache: fcis-28761.pdf plain text: fcis-28761.txt item: #470 of 872 id: fcis-28793 author: Luo, Jie; Ye, Jufeng title: Research on Object Defect Detection of Automated Pipeline Based on Cognex Camera date: 2024 words: 1495 flesch: 49 summary: This paper investigates the application of Cognex cameras in object defect detection on automated pipeline. When the external light is dim, the camera has a flash fill function to ensure the stability of the captured images, which is conducive to identifying material defects and reducing the probability of misidentification. keywords: camera; detection; material; object cache: fcis-28793.pdf plain text: fcis-28793.txt item: #471 of 872 id: fcis-28893 author: Qiu, Xiangmian; Zhang, Yali; Zhao, Yichen; Li, Jinzhao title: A Review of Text-Based Pedestrian Retrieval Methods date: 2024 words: 8365 flesch: 40 summary: Methods of Text-based Pedestrian Retrieval Text-based pedestrian retrieval aims to retrieve images of specific pedestrians through textual descriptions, and its core challenge lies in bridging the inherent gap between the two modalities and realizing cross-modal alignment between image features and text features. First bi-directional LSTM extracts text features and understands potential semantic dependencies between words, similar to the visual scene graph module, the text scene graph module detects objects present in the text and predicts the relationships between them, and at the same time, a graph attention convolutional layer is used to obtain structured text semantic features, and finally, the structured semantic text features and the initial text features are fused, which are mapped by the joint embedding layer into the shared feature space. keywords: alignment; attention; cross; features; image; information; loss; matching; methods; model; module; network; pedestrian; pedestrian retrieval; retrieval; text; training cache: fcis-28893.pdf plain text: fcis-28893.txt item: #472 of 872 id: fcis-28908 author: Zhang, Zhiqiang title: Implementing Insect Classification Based on Convolutional Neural Networks and Tensorflow date: 2024 words: 3106 flesch: 42 summary: Traditional insect image classification requires manual extraction of image features, a process that is both time-consuming and labor-intensive, and the accuracy of the identification results is relatively low. This processing strategy not only improves computational efficiency but also reduces information redundancy to some extent, thereby helping convolutional neural networks more effectively extract and utilize image features. keywords: accuracy; classification; data; image; insect; learning; model; network; rate cache: fcis-28908.pdf plain text: fcis-28908.txt item: #473 of 872 id: fcis-29028 author: Hu, Jianping title: Optimization Strategy of VR Exhibition Hall Design based on Eye Tracking Technology date: 2025 words: 3251 flesch: 30 summary: The results show that VR exhibition design incorporating eye-tracking technology can effectively enhance the educational effect and provide valuable guidance for the design optimization of future VR exhibition halls. Conclusion This study provides valuable real-time data and objective feedback for VR exhibition design through the use of eye- tracking technology, which makes the layout and presentation of exhibition content more scientific and precise. keywords: attention; data; design; exhibition; eye; learning; students cache: fcis-29028.pdf plain text: fcis-29028.txt item: #474 of 872 id: fcis-29036 author: Zhong, Xin; Luo, Li; Yu, Xiangyang; Cai, Yefan; Hong, Weibing title: Design and Implementation of an Automatic White Sugar Impurity Detection System based on Multispectral Imaging date: 2025 words: 3750 flesch: 39 summary: In the task of white sugar impurity detection, the impurities are typically small and have a low contrast with the background (white sugar). 11 The detection results indicate that the model performs well in the practical application of white sugar impurity detection, achieving efficient and accurate impurity identification. keywords: accuracy; data; detection; image; impurities; impurity; model; multispectral; sugar; system cache: fcis-29036.pdf plain text: fcis-29036.txt item: #475 of 872 id: fcis-29170 author: Zhang, Xin; Huang, Miao; Tao, Lili; Zhang, Shuping; Hu, Zhihua title: Research on Sensorless FOC Method of PMSM based on ADRC date: 2025 words: 5817 flesch: 61 summary: Sliding mode control of permanent magnet synchronous motor speed control system. Simulation model diagram of NLADRC+EKF control system 18 Table 1. keywords: control; ekf; figure; k k; motor; seconds; speed; state; system cache: fcis-29170.pdf plain text: fcis-29170.txt item: #476 of 872 id: fcis-29171 author: Ouyang, Ke; Chen, Jin; Cao, Zhongtao; Li, Wenqiang title: The Simulation of Pose Control for Stewart Platform Based on Gain-Enhanced PID with Generalized Boolean Algebra date: 2025 words: 3587 flesch: 48 summary: This paper proposes a gain- enhanced PID control method optimized by generalized Boolean algebra, applying Boolean algebraic logic control strategies to traditional PID control to improve parameter adaptability and real-time control performance. Due to the strong coupling, nonlinearity, significant interference, and the difficulty of establishing mathematical models, as well as the relatively poor dynamic performance and adaptability of traditional PID controllers, this paper addresses the high real- time and positioning accuracy requirements of the six-degree- of-freedom parallel platform. keywords: algebra; control; controller; gain; pid; pid control; platform; stewart; system cache: fcis-29171.pdf plain text: fcis-29171.txt item: #477 of 872 id: fcis-29191 author: Qi, Binting; Zhai, Hanming; Bu, Yunyang; Han, Zhuxuan; Bu, Fanliang title: Cyber Violence Text Classification Model Based on Graph Convolutional Networks and Syntactic Parsing date: 2025 words: 4666 flesch: 43 summary: Text classification is a key task in natural language processing, aimed at assigning text content to defined categories. Text Classification The traditional methods for text classification include Support Vector Machine (SVM)[1], Naive Bayes (NB)[2], K- 30 Nearest Neighbor Algorithm (KNN)[3], Decision Tree Algorithm[4], etc. keywords: bert; classification; cyber; document; gcn; graph; information; model; networks; nodes; text; violence; word cache: fcis-29191.pdf plain text: fcis-29191.txt item: #478 of 872 id: fcis-29224 author: Tu, Hao; Zhang, Ping; Cao, Tie title: Integration and Optimization of Cloud and Edge Computing in the Application Research of Cloud-based Management Platform for Airport Restricted Area Passes date: 2025 words: 2421 flesch: 37 summary: A cloud-edge collaborative architecture is proposed to enhance the efficiency of pass management, ensure data security, and optimize user experience. (2) Data Security and Privacy Requirements Pass data in airport restricted areas involves sensitive information such as personal identity details and access permissions, making data security and privacy protection particularly critical. keywords: airport; cloud; computing; data; edge; management; pass; security cache: fcis-29224.pdf plain text: fcis-29224.txt item: #479 of 872 id: fcis-29228 author: Zhu, Bailin; Shi , Yan title: Simulation Analysis of Powered Parachute Motion Characteristics based on Motor Thrust and Flap Deflection Control date: 2025 words: 4577 flesch: 54 summary:     1 1 3cG cAR cAB pA pG pth p cI pIF F F F F F F m L L         4 1 1 1 1 1 0T pA pth p pc p m M c pc cAR cAB cI M M J TM c R F crM M M                    1 2 1 0 0 1 TTT T T m pT cT pc m T pc c L L T R k             1c cG cAR cABF F F F    At this point, the 8-degree-of-freedom model of the distributed power parachute has been established.       s c s c c T cG c c c c c cF m g         keywords: c c; control; coordinate; parachute; parafoil; system; velocity; wing cache: fcis-29228.pdf plain text: fcis-29228.txt item: #480 of 872 id: fcis-29233 author: Hua, Xuequan title: Full-bridge DC-DC Converter based on Linear Active Disturbance Rejection Control date: 2025 words: 3890 flesch: 55 summary: In the traditional closed-loop control mode of DAB converter, PI controller is used to adjust the shift ratio and then control the transmission power of the system. Circuit Topology of DAB Converter Figure 1 shows the circuit topology structure diagram of DAB converter. keywords: control; converter; dab; disturbance; figure; output; power; system; voltage cache: fcis-29233.pdf plain text: fcis-29233.txt item: #481 of 872 id: fcis-29234 author: Gu, Chenyu; Du, Hong; Zhang, Xiaozheng; Wang, Ying; Yang, Zhonglin; Liu, Gaotian; Zhang, Chuan; Sun, Lei title: A Vehicle Re-Identification Algorithm for Long-Distance Small Targets Combining YOLOv8 Object Detection Algorithm date: 2025 words: 3514 flesch: 35 summary: Suppression of Redundant Information: Background or irrelevant information in images of small targets at long distances can interfere with the extraction of target features. The introduction of the Bottleneck Attention Mechanism enhances the model’s ability to adapt to multi-scale information by automatically adjusting the attention weights across feature map channels, allowing the model to extract useful information from various scales. keywords: attention; detection; ema; feature; identification; network; object; vehicle; yolov8 cache: fcis-29234.pdf plain text: fcis-29234.txt item: #482 of 872 id: fcis-29257 author: Wei, Jia; Sun, Xiangguo title: Bimodal Emotion Recognition based on Sichuan Dialect date: 2025 words: 3458 flesch: 46 summary: With the rapid rise of artificial neural networks, especially deep learning technology, the performance of emotion recognition models has been greatly improved, laying a solid foundation for emotion recognition in more complex language environments. The model adopts the dual-modal fusion strategy of Mel spectral features (MFCCs) and text features, uses dynamic convolutional network (ODConv) and convolutional block attention module (CBAM) to extract features, and combines the Text-CNN model for text sentiment analysis. keywords: attention; channel; emotion; feature; input; model; recognition; speech; text cache: fcis-29257.pdf plain text: fcis-29257.txt item: #483 of 872 id: fcis-29274 author: Lu, Jiang title: Identifying Depression Using Machine Learning date: 2025 words: 3776 flesch: 55 summary: For depression data set, a machine learning model is used to predict whether people suffer from depression. Flow chart of depression prediction model based on machine learning After the construction of the model, Accuracy rate, accuracy rate, recall rate, F1-Score and AUC indicators are usually used to evaluate the prediction results of various machine learning algorithms for depression recognition. keywords: catboost; data; depression; health; learning; machine; model; rate; set; survey cache: fcis-29274.pdf plain text: fcis-29274.txt item: #484 of 872 id: fcis-29275 author: Zhang, Jian; Chen, Kang title: Research on Downhole Two-Phase Flow Parameter Measurement Method Based on Deep Neural Networks date: 2025 words: 2041 flesch: 44 summary: Long Short-Term Memory Networks (LSTM) can handle this dependence well, and flow measurement methods based on LSTM can improve the measurement accuracy of liquid phase flow to meet industrial measurement requirements. Multilevel well modeling in aggregation-based nonlinear multigrid for multiphase flow in porous media [J]. keywords: downhole; flow; gas; measurement; model; parameter; phase cache: fcis-29275.pdf plain text: fcis-29275.txt item: #485 of 872 id: fcis-29342 author: Wang, Qisen; Hou, Junhan; Zhong, Zihe title: Optimization of Crop Planting Strategies Based on Monte Carlo Simulation and Greedy Algorithm date: 2025 words: 3382 flesch: 54 summary: In this study, crop planting strategies were optimized for a village based on Monte Carlo simulation and greedy algorithm. Introduction The aim of this paper is to develop crop planting scenarios for the period from 2024 to 2030 by building a goal planning model and combining various computer algorithms keywords: crop; model; planting; price; sales; volume; year cache: fcis-29342.pdf plain text: fcis-29342.txt item: #486 of 872 id: fcis-29349 author: Wu, Wendong; Yao, Minmin title: Optimization of Underwater Images Based on Gray World Algorithm and Jaffe-McGlamery Models date: 2025 words: 1861 flesch: 49 summary: The results show that the proposed method performs significantly in improving the visual quality and various evaluation metrics of underwater images, especially in complex underwater environments, and the combination of multiple models can be applied to cope with image degradation more effectively. In summary, this study provides a systematic enhancement framework for underwater image processing, emphasizes the importance of customizing the processing strategy according to the type of image degradation, and promotes the development of underwater image technology. keywords: algorithm; color; image; light; model cache: fcis-29349.pdf plain text: fcis-29349.txt item: #487 of 872 id: fcis-29350 author: Shui , Peilin; Zhang, Zeyu; Xie, Caixing; Zhao, Jiaying; Lu, Zilun title: Optimization of Environmental Conditioning Equipment Based on Particle Swarm Optimization Algorithm and Genetic Algorithm date: 2025 words: 2768 flesch: 43 summary: Factor Analysis In this section, we study the optimization of various aspects of air conditioner design and the effect of placement of air conditioner on temperature regulation and construct the best optimization model of air conditioner shape to achieve the best temperature regulation. Firstly, the particle swarm optimization algorithm (PSO) is applied to simulate the indoor temperature change for the placement of air conditioners, the location of the inlet and outlet, and the direction of airflow to design the optimal shapes and sizes to improve the temperature control efficiency. keywords: air; algorithm; conditioner; effect; optimization; purifier; shape cache: fcis-29350.pdf plain text: fcis-29350.txt item: #488 of 872 id: fcis-29385 author: Ruan, Xingyan; Luo, Li; Yu, Xiangyang; Cai, Yefan; Hong, Weibin title: Rapid Textile Fibers Classification Technology Based on Near-Infrared Spectroscopy and Machine Learning date: 2025 words: 4168 flesch: 45 summary: Although these issues increase the difficulty of sample classification, properly handling spectral drift and fluctuations can enhance the robustness of the classification model, reduce noise interference, and uncover potential information, thereby improving the scientific validity and accuracy of the classification. When the class distribution of sample data is imbalanced, accuracy may not fully assess the model's performance. keywords: accuracy; auc_macro; classification; data; feature; fiber; model; results; samples; svm cache: fcis-29385.pdf plain text: fcis-29385.txt item: #489 of 872 id: fcis-29392 author: Liao, Wenbing; Li, Wenwen title: Research on DETR-based Weed Detection Algorithm date: 2025 words: 3442 flesch: 50 summary: Model detection results Fig. Wenbing Liao 1 and Wenwen Li 2 1 School of Information and Control Engineering, Jilin Institute of Chemical Technology, Jilin Jilin 132022, China 2 School of Mechanical and Control Engineering, Baicheng Normal College, Baicheng, Jilin 137000, China Abstract: To address the problem of complex field conditions and high similarity between corn seedlings and weeds, this study proposes an improved DETR (Detection Transformer) model for weed detection in corn fields, which uses the CBAM convolutional attention mechanism in the DETR model, and uses a focal loss function instead of the traditional cross-entropy loss function to balance the number of positive and negative class samples of the data. keywords: attention; detection; detr; feature; loss; map; model; weed cache: fcis-29392.pdf plain text: fcis-29392.txt item: #490 of 872 id: fcis-29528 author: Zhang, Hongze; Pan, Huaxiang title: Design of Intelligent Agricultural Greenhouse System date: 2025 words: 3147 flesch: 52 summary: It integrates various sensors, including environmental temperature and humidity sensors, soil moisture sensors, and light intensity sensors. Design of temperature and humidity acquisition and control system for agricultural greenhouse based on microcomputer [J]. keywords: greenhouse; humidity; light; module; pin; sensor; system cache: fcis-29528.pdf plain text: fcis-29528.txt item: #491 of 872 id: fcis-29529 author: Li, Mu; Xia, Yulin; Hu , Wei; Zhang, Ziyi; Zhang, Chengchen title: Research on the Construction of TCM Diagnosis Model based on Large Language Model date: 2025 words: 3598 flesch: 47 summary: Fine-tuning of the Model Automatic evaluation of language models is a common and popular evaluation method, mainly because it saves a lot of time and cost by not requiring human involvement, and it usually uses standard metrics or indicators to evaluate the performance of the model, such as BLEU (Bilingual Evaluation Understudy) This lack of data directly affects the training and validation of intelligent discursive models, making it difficult for model performance to meet expected requirements. keywords: application; chest; data; evidence; language; medicine; model; syndrome; tcm; training; tuning cache: fcis-29529.pdf plain text: fcis-29529.txt item: #492 of 872 id: fcis-29530 author: Ruan, Conghao; Su, Wei title: Research on "Robot+" Campus Intelligent Logistics Simulation Based on PQFactory Platform date: 2025 words: 2894 flesch: 38 summary: Integrated Debugging The joint debugging of PQFactory and PLC is one of the core technologies in campus intelligent logistics systems, which combines virtual simulation and real-time communication technology to comprehensively simulate and optimize production lines. Design and implementation of campus express delivery system with visual robot arm keywords: campus; delivery; express; logistics; plc; pqfactory; robot; signal; simulation; system cache: fcis-29530.pdf plain text: fcis-29530.txt item: #493 of 872 id: fcis-29531 author: Yu, Xin; Zhang, Mohan; Li, Jiayao; Wang, Xinrui; Jin, Shumin; Li, Qian title: Graph Neural Network Graph Embedding Optimization Method for Vascular Stress Prediction date: 2025 words: 3858 flesch: 33 summary: Focus on the study of the influence of blood vessel bending degree, fix other geometric and physical parameters of blood vessels, generate blood vessel model data sets with different bending degrees by adjusting the bending radius and bending angle of blood vessels, and then investigate the mechanism of bending on blood vessel stress. With the rapid development of machine learning technology, especially graph neural network, it is possible to construct an efficient reduced-order model for vascular stress prediction, which is also the core goal of this study. keywords: blood; data; graph; method; model; prediction; stress; vascular; vessels cache: fcis-29531.pdf plain text: fcis-29531.txt item: #494 of 872 id: fcis-29592 author: Liu, Jiahui; Peng, Gaohui title: Water Supply and Demand Index of Henan Province Spatial and Temporal Correlation Analysis date: 2025 words: 5524 flesch: 40 summary: Water resources in the eastern part of the region mainly come from the Yellow River tributaries and groundwater, and water resources are generally stable, but tensions can still occur during peak water use periods. The region in the south is not only abundant in water resources, but also has high correlation between neighboring cities; from Table 9 , it can be seen that the three cities in west Henan are in the state of water resources surplus all the year round, and the correlation between cities is also high, with the support degree of 58%, 66%, and 75%; from Table 10, it can be seen that the cities in the east Henan are Kaifeng, which has a permanent shortage of water resources, and the cities with permanent surplus are Shangqiu and Zhoukou, with the support degree of 66%, of which the correlation rule is 66%, with the support degree of 66%. keywords: cities; correlation; demand; henan; resources; supply; support; surplus; water; water resources; years cache: fcis-29592.pdf plain text: fcis-29592.txt item: #495 of 872 id: fcis-29594 author: Li, Junfeng; Chen, Qian; Du, Yang; Lijiang, Donghui; Liang, Zhen title: Time Series Modeling and Forecasting Analysis of Energy Consumption in a Rare Earth Workshop date: 2025 words: 3226 flesch: 41 summary: The ADF test is a statistical method used to verify the stationarity of time series data, which is crucial for ensuring the accuracy of predictive models. First, time series data is collected and tested for stationarity; if the data is non- stationary, differencing is applied to achieve stationarity. keywords: arima; autocorrelation; carbon; consumption; data; energy; model; time cache: fcis-29594.pdf plain text: fcis-29594.txt item: #496 of 872 id: fcis-29595 author: none title: Retraction date: 2025 words: 65 flesch: 55 summary: Frontiers in Computing and Intelligent Systems ISSN: 2832-6024 | Vol. 11, No. 2, 2025 Retraction At request of the authors, this article has been retracted by Darcy & Roy Press in light of clear evidence that the results and conclusions are no longer valid. We thank the authors for notifying us so that the publication record can be amended accordingly. keywords: retraction cache: fcis-29595.pdf plain text: fcis-29595.txt item: #497 of 872 id: fcis-2965 author: Cai, Jiaowu; Li, Liangyu; Zhang, Zhijun title: Application of Improved DV-Hop algorithm in Wireless Sensor Network date: 2022 words: 3322 flesch: 54 summary: In this paper, the area of anchor node by calculating whether the anchor node is collinear:𝑆𝑛 𝑆𝑛 = | 𝑥𝑖 𝑦𝑖 1 𝑥𝑗 𝑦𝑗 1 𝑥𝑘 𝑦𝑘 1 | (7) Assume that (𝑥𝑖 , 𝑦𝑖) , (𝑥𝑗 , 𝑦𝑗) and (𝑥𝑘 , 𝑦𝑘) are the coordinates of 3 anchor nodes randomly distributed,𝑆𝑛is the triangle area composed of anchor nodes. Deficiency of the D V-Hop algorithm (1) The topological relationship of anchor nodes will directly affect the positioning accuracy of wireless sensor nodes. keywords: algorithm; anchor; error; hop; hop algorithm; localization; nodes; particle cache: fcis-2965.pdf plain text: fcis-2965.txt item: #498 of 872 id: fcis-2966 author: Song, Zheng; Luo, Shu title: Application of machine learning and data mining in manufacturing industry date: 2022 words: 6098 flesch: 42 summary: The presence of large volumes of manufacturing data is likely to make ML and DM even more important in the coming years. Because manufacturing data is often characterized by multiple sources (i.e., machine, product, operator), heterogeneity, and noise, some data preprocessing steps such as standardization, attribute construction, feature selection, and elimination of missing values have been considered in many studies. keywords: clustering; data; industry; learning; machine; machine learning; manufacturing; manufacturing data; methods; mining; process; processing; quality; time cache: fcis-2966.pdf plain text: fcis-2966.txt item: #499 of 872 id: fcis-2967 author: Wang, Guangsheng; Lei, Zhiyi; Yu, Tong; Zhang, Cheng; Sun, Haijun; Sousa, Jéssica Saturnino Sabino de title: Logistics Performance Evaluation in West Africa date: 2022 words: 5456 flesch: 53 summary: By betting in infrastructure reform and resource integration, West African countries might achieve the desired goal of construction, industrialization and a better layout of sea and airports that enables the interconnection of transportation infrastructures. West African countries are mostly resource rich countries, and their economic development largely depends on resource exports. keywords: africa; countries; criteria; development; evaluation; ghana; logistics; performance; port; region; senegal; time; west; west africa cache: fcis-2967.pdf plain text: fcis-2967.txt item: #500 of 872 id: fcis-2968 author: Li, Anmengdie; Zhang, Jinglei; Wang, Kaili title: Study on the Correlation between Drivers' Anger Language and Driving Anger date: 2022 words: 4498 flesch: 49 summary: In the following research, anger language can be used as a feature vector for angry driving recognition system according to the classification. To sum up, anger language research focuses on speech 62 recognition, using typical speech feature parameters such as Mel-Frequency Cepstral Coefficients (MFCC), Linear Prediction Coefficients (LPC), Linear Predictive Cepstral Coefficients (LPCC) to model and complete anger emotion recognition; model performance is improved on the basis of face recognition, to prove the correlation between voice and emotion recognition. keywords: anger; drivers; driving; emotion; evaluation; frequency; language; question; questionnaire; recognition; weight cache: fcis-2968.pdf plain text: fcis-2968.txt item: #501 of 872 id: fcis-2969 author: Lan, Jianghai; Lin, Guojun title: A Review of Facial Expression Recognition date: 2022 words: 2041 flesch: 51 summary: We summarize some widely used public data sets for facial expression recognition; The basic flow of facial expression recognition is briefly introduced. A face with arbitrary posture or even extreme profile can be positively transformed or rotated through a codec structure generator, which has far-reaching significance for the study of facial expression recognition with low robustness in the field. keywords: convolution; data; expression; layer; network; recognition cache: fcis-2969.pdf plain text: fcis-2969.txt item: #502 of 872 id: fcis-2970 author: Wang, Jianrong; Li, Naiyi title: Chinese Text Sentiment Classification Based on ERNIE and BiLSTM-AT date: 2022 words: 4530 flesch: 50 summary: Text emotion classification model based on ERNIE and BiLSTM-AT The text emotion classification model combined with ERNIE and BilSTM-AT is shown in Figure 1 below. Text emotion classification model based on ERNIE and BiLSTM-AT 2.1. keywords: classification; emotion; ernie; information; layer; model; sentence; text; training; vector; word cache: fcis-2970.pdf plain text: fcis-2970.txt item: #503 of 872 id: fcis-2971 author: Yang, Le; Chen, Hua title: A Network Intrusion Detection Model Based on Principal Component Analysis and Random Forest date: 2022 words: 3559 flesch: 49 summary: Point value PCA classifier is selected for initial data, and forest density is selected for random forest classification. Abstract: Network intrusion data has the characteristics of high dimension, nonlinearity and redundancy. keywords: classification; data; decision; detection; forest; information; intrusion cache: fcis-2971.pdf plain text: fcis-2971.txt item: #504 of 872 id: fcis-29823 author: Miao, Chunming title: Modeling and Simulation Research on the Hydraulic System of the Blade of an Unmanned Bulldozer date: 2025 words: 2291 flesch: 54 summary: [2] Guo, G., Gong, L.H. (1998) Research on fuzzy control of cutting depth of bulldozer blade. Flow Rate Curves of the Hydraulic Cylinder Chambers 82 As shown in Figure 7, the red and blue curves represent the flow rate changes in the working chambers of the lifting and tilting hydraulic cylinders, respectively. keywords: blade; cylinder; seconds; system; tilting cache: fcis-29823.pdf plain text: fcis-29823.txt item: #505 of 872 id: fcis-29830 author: Guan, Weichun; Zhang, Yuanyuan; Lv, Xinshu; Lv, Shuyun; Lin, Mao; Liu, Zhengyang title: Feature Recognition of Ultrasound Breast Images Based on Improved DSA-U++ date: 2025 words: 3885 flesch: 45 summary: Deep learning can learn more image features from a large amount of image data, which is of great significance in the field of image processing [6]. The experimental results show that the model also improves in classification accuracy compared to the traditional model, which verifies the effectiveness of the proposed method in medical image feature extraction and classification tasks. keywords: breast; classification; convolution; feature; image; information; model; module; net++; output; ultrasound cache: fcis-29830.pdf plain text: fcis-29830.txt item: #506 of 872 id: fcis-29831 author: Chen, Shitian; Su, Chengyue title: Higher Order Predefined-time Sliding Mode Control for PMSM With Uncertain Disturbance date: 2025 words: 4167 flesch: 63 summary: [7] A. Wang, X. Jia, and S. Dong, “A new exponential reaching law of sliding mode control to improve performance of permanent magnet synchronous motor,” IEEE Trans. In [8], a novel Higher-Order Super Twisting Sliding Mode Control (HO-STSMC) was proposed to achieve speed control of the Permanent Magnet Synchronous Motor (PMSM) with finite-time convergence. keywords: control; disturbance; mode; pmsm; speed; time cache: fcis-29831.pdf plain text: fcis-29831.txt item: #507 of 872 id: fcis-29832 author: Zang, Fengtao; Liu, Wei title: Research on Speed Control System of AC Asynchronous Motor date: 2025 words: 1740 flesch: 45 summary: Therefore, this paper concentrates on studying motor speed control methodologies. Research on AC asynchronous motor speed regulation based on constant voltage frequency ratio. keywords: control; motor; simulation; speed; system cache: fcis-29832.pdf plain text: fcis-29832.txt item: #508 of 872 id: fcis-29838 author: Lv, Hang; Zhang, Longlong; Cao, Qiusheng title: A Method for Accelerating the Loading of TIFF Files Based on Memory-Mapped File Technology date: 2025 words: 3787 flesch: 59 summary: In this study, we proposed FastTIFF, a rapid loading method for large TIFF files, aiming to enhance the decoding efficiency of TIFF files through memory-mapped technology and multi-threaded parallel processing. Its significant performance improvements provide a new technical approach for the field of TIFF file processing and lay a solid foundation for future optimization and applications. keywords: data; fasttiff; file; image; loading; memory; processing; task; thread; tiff cache: fcis-29838.pdf plain text: fcis-29838.txt item: #509 of 872 id: fcis-29907 author: Li, Xinlin; Fan, Changhe; Su, Chengyue title: Self-Supervised Learning for Speech-Based Detection of Depressive States date: 2025 words: 2474 flesch: 50 summary: In recent years, self-supervised learning has achieved success in pre-training voice signals and has been widely applied to data-sparse related tasks. CNN-BiLSTM: Shows the smallest gender difference, indicating that this model is more stable in processing speech features of different genders. keywords: bilstm; cnn; depression; model; pre; self; speech; training cache: fcis-29907.pdf plain text: fcis-29907.txt item: #510 of 872 id: fcis-29918 author: Liu, Xin title: Email Security Detection Solution Based on Multi-Scenario Classification date: 2025 words: 3464 flesch: 54 summary: Nowadays, phishing attacks are most commonly carried out through emails, which has led to extensive research on phishing email attack detection both at home and abroad. The issue of how to detect phishing emails from a vast number of emails has long drawn significant attention. keywords: detection; emails; features; gate; information; model; number; phishing; research; results cache: fcis-29918.pdf plain text: fcis-29918.txt item: #511 of 872 id: fcis-29982 author: He, Gengyun; Wang, Gang title: Design and Implementation of an Einstein Chess Intelligent Gaming System Based on Policy-Value Network date: 2025 words: 5591 flesch: 32 summary: Deep Learning Applications Deep learning technology has introduced promising opportunities for game AI systems. Research on NoGo game system based on AlphaZero[J]. keywords: chess; design; einstein; game; learning; loss; mcts; network; node; performance; policy; research; stochastic; system; training; value cache: fcis-29982.pdf plain text: fcis-29982.txt item: #512 of 872 id: fcis-29986 author: Zhou, Bingxu; Yu, Yang title: Prediction of the Remaining Life of Rolling Bearings based on the Classification of Degradation States date: 2025 words: 2397 flesch: 48 summary: Abstract: view of the fact that the healthy running time of rolling bearings in actual working conditions lasts for a long time, and the vibration signal fluctuation in the healthy operation stage is relatively stable, and it is difficult to extract useful degradation information from them, a remaining life prediction model based on the classification of degradation states based on the hidden Markov model is proposed. [4], an adaptive state division method is adopted, the sliding window is used to continuously update the early warning range of the 3σ criterion, and the continuous trigger mechanism is combined to adaptively determine the degradation start time for state division. keywords: bearing; degradation; frequency; model; prediction; state; whale cache: fcis-29986.pdf plain text: fcis-29986.txt item: #513 of 872 id: fcis-30006 author: Zhang, Lei; Li, Zhaoqing; Wang, Jinbing title: Research on Intelligent Workshop Monitoring System Technology in Tobacco Logistics Center date: 2025 words: 3364 flesch: 39 summary: Construction of Key Elements Model of Digital Twin Workshop DTws=∑ ∪∑ ∪∑ ∪ ∑ (1) Where :DTws represents the digital twin model of the production workshop scenario; ∑ denotes the total set of workshop equipment models, with n being the number of devices; ∑ indicates the aggregated material models in the workshop, where m corresponds to the quantity of work-in-progress products; ∑ refers to the collection of environmental models, with q representing the number of environmental monitoring parameters; ∑ encompasses the operator models, where p signifies the total staff count. Data Collection: Workshop production line equipment, sensors, and control components are all equipped with network ports, enabling them to connect to the PLC (Siemens S7-1500, CPU1518) central control cabinet for unified data management. keywords: data; digital; equipment; level; line; model; modeling; monitoring; production; system; twin; workshop cache: fcis-30006.pdf plain text: fcis-30006.txt item: #514 of 872 id: fcis-30007 author: Zhang, Guangmao; Chen, Jiabei; Yuan, Jing; Ma, Yunfei title: Multi-channel Data Display Software based on fNIRS date: 2025 words: 2180 flesch: 58 summary: In addition, the software has shown significant advantages in improving the efficiency of fNIRS data processing, promoting scientific research cooperation and result exchange, and provides strong support for the further promotion and application of fNIRS technology. Save data logic (5) The waveform can be cleared with one click to facilitate the collection of multi-person data. 2.3. keywords: data; display; figure; port; software; waveform cache: fcis-30007.pdf plain text: fcis-30007.txt item: #515 of 872 id: fcis-30008 author: Shen, Yue; Yu, Yang title: Bearing Acoustic Emission Signal Processing based on Improved SGMD date: 2025 words: 3631 flesch: 38 summary: This method significantly improves the robustness of signal decomposition and the ability to extract fault features, and provides an effective tool for the diagnosis of AE bearings under complex working conditions. In this study, an improved SGMD (ISGMD) method is proposed, which improves the adaptability of the algorithm to different signals by constructing an adaptive threshold mechanism, uses the mirror extension technology to eliminate the endpoint effect, and introduces the entropy theory for effective component screening and signal reconstruction. keywords: components; decomposition; entropy; fault; figure; mode; noise; signal; threshold cache: fcis-30008.pdf plain text: fcis-30008.txt item: #516 of 872 id: fcis-30018 author: Zhou, Yao; Zhao, Lixin; Bu, Fanliang title: Research on the Fast-GwcNet 3D Reconstruction Method for Crime Scenes date: 2025 words: 4196 flesch: 48 summary: Firstly, the scene environment often suffers from interference such as motion blur and non- Lambertian reflections (e.g., bloodstains, glass), which reduces the reliability of feature matching. MAPM extracts multi-level feature maps to capture information at different scales and enhances similarity measurement through self-learned weight patch matching of local information. keywords: cost; disparity; feature; information; map; matching; method; module; reconstruction; stereo; volume cache: fcis-30018.pdf plain text: fcis-30018.txt item: #517 of 872 id: fcis-30019 author: Geng, Haoqi; Lu, Tianliang; Huang, Wanxin; Ding, Bowen title: Deepfake Detection Technology Integrating Spatial Domain and Frequency Domain date: 2025 words: 5774 flesch: 51 summary: In view of the fact that previous deepfake research has paid relatively little attention to robustness testing and lacks comparable data, this chapter selected mainstream face forgery detection models, including Xception, FaceXray, LipForensics, CADDM, LAA-Net, as the comparison object. The FaceShifter dataset covers people of multiple races, genders, and ages, as well as multiple expressions, poses, and lighting conditions, which provides important data support for studying the application of faceshifter technology in forgery video detection. BioDeepAV keywords: accuracy; dataset; deepfake; detection; domain; face; feature; frequency; frequency domain; information; model; network; transform; videos cache: fcis-30019.pdf plain text: fcis-30019.txt item: #518 of 872 id: fcis-30110 author: Li, Minmin; Diao, Yanyu; Wang, Xin title: Construction and Implementation of Coal Mine Safety Knowledge Graph Based on Historical Accidents date: 2025 words: 3142 flesch: 54 summary: Coal Mine Accident Data Entity Recognition Text entity recognition of coal mine accidents is a key step in the construction of coal mine safety knowledge graph. Although in recent years in the country's continuous transformation of the coal mining industry, coal mine safety accidents have been reduced year by year, but in order to better prevent the occurrence of coal mine accidents, this paper through the coal mine safety network on the coal mine accident case text data, to build the knowledge graph in the field of coal mine safety, through the knowledge graph will be associated between the accident, so as to analyze it, to find out the similarities between the accidents, and to avoid similar accidents from reoccurring. keywords: accident; bilstm; coal; data; graph; knowledge; model; safety cache: fcis-30110.pdf plain text: fcis-30110.txt item: #519 of 872 id: fcis-30111 author: Zhang, Jun; Zhang, Jiaqi title: Multimodal Data Fusion for Digital Monitoring of Railway Vehicle Wheelset Health Status date: 2025 words: 4222 flesch: 43 summary: Comparison of wheelset maintenance data before and after deployment of the multimodal fusion system References [1] Lourenço A, Ribeiro D, Fernandes M, et al. Comparison of fault identification accuracy between multimodal fusion model and unimodal model in different cases 75 Figure 7. keywords: data; fault; feature; fusion; health; model; monitoring; multimodal; railway; speed; system; time; wheelset cache: fcis-30111.pdf plain text: fcis-30111.txt item: #520 of 872 id: fcis-30132 author: Hao, Yun title: The Strengthen and Depth of Data Legislation Research: -- Literature Visualization Analysis based on Cite Space and VOS Viewer date: 2025 words: 5962 flesch: 41 summary: This article conducted a statistical analysis of the authors and the number of publications in the field of data legislation research and found that the first author Huang Daoli had 6 publications, so the minimum single publications of the core researchers in the field of data legislation should be based on Mp=0.749np√ Np max=0.794 6=1.8347 as the standard, which is close to 2 publications. Cooperative network map in the field of data legislation research in China From this, based on the analytical data in Figure 2 and Table 5, we can see that no good cooperative relationship has been formed between the authors of the published research on data legislation. keywords: china; data; data legislation; information; law; legislation; number; personal; protection; research; security; university cache: fcis-30132.pdf plain text: fcis-30132.txt item: #521 of 872 id: fcis-30136 author: Huang, Dongxuan; Sun, Mingge; Ye, Sen; Chai, Jiaxuan title: Improvement and Implementation of a Potato Recognition Algorithm Based on YOLOv8 date: 2025 words: 3134 flesch: 42 summary: The improvements include: introducing DynamicConv in the backbone network to enhance model representation capability; replacing the C2f module in the backbone network with C2f_SAConv to strengthen feature extraction in object detection and segmentation tasks; incorporating Slim-neck in the Neck layer to reduce model parameters and floating-point operations; and adding an EMA attention mechanism to improve the model's focus on different potatoes. DynamicConv dynamically selects or combines different convolution kernels based on input samples, enabling the network structure to adaptively adjust its parameters according to varying input data. keywords: algorithm; convolution; detection; feature; information; model; network; potato; precision; recognition; yolov8 cache: fcis-30136.pdf plain text: fcis-30136.txt item: #522 of 872 id: fcis-30144 author: Ma, Zhiyuan; Wu, Jie title: Design of an LLM-Driven Personalized Learning Resource Recommendation System: -- A Comparative Study date: 2025 words: 2332 flesch: 30 summary: Developers need not consider local computational resources for training and deploying recommendation models, which reduces the usage threshold of recommendation platforms. Prompt Tuning In recommendation systems and LLM applications, Fine - Tuning and Prompt Tuning is essential to enhance the LLM's task performing ability.[2] Since the platform is implemented by connecting to existing LLMs through an API for recommendations, Prompt Tuning is used to fine-tune the LLM. keywords: course; learning; llm; llms; recommendation; resources; system; user cache: fcis-30144.pdf plain text: fcis-30144.txt item: #523 of 872 id: fcis-30145 author: Shao, Lidan; Liu, Yongping; Shao, Jianxin title: Research on the Application of Artificial Intelligence Technology in Intelligent Logistics Scheduling date: 2025 words: 2207 flesch: 30 summary: Abstract: Smart logistics refers to the use of advanced information technology and logistics management methods to optimize and improve the efficiency and service quality of logistics transportation, warehousing, distribution and other links through intelligent and networked means. Through artificial intelligence algorithms, valuable information can be extracted from massive logistics data efficiently, providing strong support for smart logistics systems. keywords: data; intelligence; logistics; path; planning; technology; time; transportation cache: fcis-30145.pdf plain text: fcis-30145.txt item: #524 of 872 id: fcis-30146 author: Ni, Qijun; Zeng, Yinghao title: Research on Smart Campus System Architecture Design and Data Security Protection Strategy date: 2025 words: 2208 flesch: 35 summary: However, smart campus data security still faces numerous complex and severe challenges (Table 1), posing risks to the privacy and legal rights of faculty and students while potentially impacting the normal operation of schools, teaching order, and educational equity. In response to the numerous complex challenges and potential risks currently faced by data security, a series of data security protection solutions that integrate advanced technologies and scientific management concepts are innovatively proposed. keywords: architecture; campus; data; layer; management; network; security; system cache: fcis-30146.pdf plain text: fcis-30146.txt item: #525 of 872 id: fcis-30147 author: Li, Xuanyao; Guo, Jinrong title: A Blind Assistance System Based on Real-Time Object Detection, Timing Analysis and Angle Navigation date: 2025 words: 1645 flesch: 51 summary: We use the YOLOv5 model for object detection on mobile and combine it with a lightweight multi-target tracking algorithm (DeepSORT) to achieve continuous recognition of the objects in the video stream, thus providing more stable detection results. Combined with object tracking for stable temporal recognition, reducing detection jitter and ID switching. keywords: angle; blind; detection; object; tracking cache: fcis-30147.pdf plain text: fcis-30147.txt item: #526 of 872 id: fcis-30148 author: Yu, Yanqing; Wang, Qiuyan title: Research on Medical Device Measurement and Inspection System Based on Big Data Analysis date: 2025 words: 2692 flesch: 34 summary: Through the collection, storage, processing and analysis of a large amount of medical equipment data, it can achieve more accurate detection, predictive maintenance, improve the use of medical equipment safety and reliability, reduce the impact of equipment failure on patient care, maintain the continuity and high quality of medical services, provide a scientific basis for decision-making for healthcare institutions, and drive the process of digitalization and intelligent transformation of the medical industry This differentiated association field design takes into full consideration the diversity and complexity of medical data, which is conducive to the accurate management and efficient use of data, and meets the needs of the medical industry in terms of data storage, querying and analysis and other diversified applications. keywords: analysis; data; equipment; management; medical; model; storage; system; testing cache: fcis-30148.pdf plain text: fcis-30148.txt item: #527 of 872 id: fcis-30156 author: Xu, Chenyue; Wang, Rong title: Abnormal Behavior Recognition Method Based on Fine-Grained Human Dynamic Skeleton Features date: 2025 words: 2398 flesch: 32 summary: After the hierarchically decomposed graph convolution module, human skeleton features extracted from different levels are obtained. Second, a hierarchical decomposed graph convolutional network (modified from spatio- temporal graph convolutional networks) is implemented for dynamic skeleton feature extraction, coupled with an attention- guided hierarchical aggregation module for multi-level feature fusion. keywords: convolution; feature; graph; model; module; recognition; skeleton cache: fcis-30156.pdf plain text: fcis-30156.txt item: #528 of 872 id: fcis-30157 author: Li, Ping; Zhuang, Manyi; Tang, Jun; Huang, Jian title: Research on Automatic Recognition and Auxiliary Diagnosis of Artificial Intelligence in Skin Diseases date: 2025 words: 13268 flesch: 34 summary: Overall, the experimental environment was optimized for performance, reproducibility, and ethical compliance, contributing to the successful development of skin disease diagnosis models. Conclusion: The training and optimization of skin disease recognition models benefit from advanced algorithms like Adam and techniques such as early stopping. keywords: accuracy; classification; data; datasets; decision; diagnosis; disease; features; images; knowledge; learning; lesion; methods; model; performance; recognition; research; skin; skin disease; study; system; techniques; training cache: fcis-30157.pdf plain text: fcis-30157.txt item: #529 of 872 id: fcis-30203 author: Zhao, Xiaoyi; Zhang, Xinchen; Wang, Shasha title: Research on Federated Learning Algorithms Driven by Data Heterogeneity date: 2025 words: 2692 flesch: 35 summary: China Abstract: Federated Learning as a distributed machine learning paradigm enables collaborative modeling among multiple participants while preserving data privacy. Keywords: Federated Learning; Data Heterogeneity; Three-dimensional Optimization Framework; Adaptive Optimization. keywords: client; convergence; data; gradient; heterogeneity; learning; model; optimization; reference cache: fcis-30203.pdf plain text: fcis-30203.txt item: #530 of 872 id: fcis-30207 author: Luo, Jinrong; Liao, Wenzhuo; Chen, Meishi title: Design of Automobile Exhaust Emission Detection and Alarm System date: 2025 words: 4400 flesch: 54 summary: Architecture diagram of tail gas detection system As the main control chip in the center of the system detection module, it carries the data collection, transmission and processing work, but also responsible for the management of various types of external devices Air quality detection module sensor using tin dioxide (SnO2) as a gas-sensitive material, in the non-polluted air, its conductivity is low, in the polluted environment, with the increase in the concentration of polluted gases, its conductivity will increase accordingly. keywords: air; alarm; circuit; design; detection; exhaust; figure; gas; sensor; system cache: fcis-30207.pdf plain text: fcis-30207.txt item: #531 of 872 id: fcis-30252 author: Xu, Zhang; Yang, Yu title: Acoustic Emission Signal Diagnosis of Rolling Bearing Faults Based on CEEMDAN and MESSA-SVM date: 2025 words: 6501 flesch: 44 summary: Recognition of rolling bearing fault acoustic emission signal based on GA-IDBN[J]. Feature extraction of rolling bearing fault acoustic emission signal with improved wavelet threshold function and ACEWT method[J]. keywords: algorithm; bearing; components; correlation; diagnosis; emission; fault; feature; imf; messa; search; signal; solution; strategy; svm cache: fcis-30252.pdf plain text: fcis-30252.txt item: #532 of 872 id: fcis-30253 author: Zhang, Xiaoyu; Ji, Xiang; Li, Yize title: Research on Intelligent Anti-Jamming for Data Links Based on CV-R-BiLSTM-A Interference Recognition Network date: 2025 words: 3949 flesch: 46 summary: Given the current lack of interference signal recognition methods and the low overall recognition rate of existing methods, this paper proposes an interference recognition network method based on complex-valued residual bidirectional long short-term memory attention (CV-R-BiLSTM-A) to identify interference signals. In response to the current problems of fewer interference signal recognition methods and the low overall recognition rate of interference recognition in existing methods, this paper proposes the CV-R-BiLSTM-A network to recognize interference signals. keywords: bilstm; frequency; interference; modulation; network; noise; recognition; signal cache: fcis-30253.pdf plain text: fcis-30253.txt item: #533 of 872 id: fcis-30254 author: Ai, Jinkai; Zhang, Kewei; Dong, Zhenkui title: Research on the Suppression of Secondary Power Ripple in Single-Phase Pulse Rectifier Based on Improved Deadbeat-Repetitive Control date: 2025 words: 3714 flesch: 48 summary: The repetitive control method is a typical application of the internal mode principle, by introducing a periodic delay in the forward channel and constructing positive feedback, and introducing a resonant peak at the input signal fundamental and its frequency doubling, it can achieve efficient suppression of any integer harmonic, so the use of repetitive control can make the decoupling circuit effectively track the second harmonic, the structure of traditional repetitive control, This is shown in Figure 3. P(z) Q(z)z-n z-n C(z)=Krz mS(z) It integrates and improved deadbeat-repetitive control without difference, improves the inherent cycle delay problem of repeated control, realizes the tracking of the second harmonic current without difference, and improves the dynamic performance of the system. keywords: capacitor; circuit; control; current; decoupling; energy; power; ripple; system; voltage cache: fcis-30254.pdf plain text: fcis-30254.txt item: #534 of 872 id: fcis-30255 author: Li, Xiaobo; Wang, Haibiao title: Analysis of the Main Control Factors Affecting the Production Capacity of Surig Gas Field Su 53 Area date: 2025 words: 4976 flesch: 45 summary: Experts and scholars at home and abroad have also done a lot of research on the main control factors of horizontal well production capacity in different oil and gas reservoir types. (2) The pattern of horizontal well production capacity under different completion methods and single fracturing influencing factors is not obvious from the analysis of field data, which indicates that the horizontal well production capacity is affected by a combination of many factors such as geological and engineering conditions. keywords: capacity; coefficient; correlation; data; factors; fracturing; gas; production; wells cache: fcis-30255.pdf plain text: fcis-30255.txt item: #535 of 872 id: fcis-30258 author: Long, Tianchen; Wang, Yanwen; Ma, Hongqing; Cai, Chang; Liu, Feng title: Design of Unmanned Aerial Vehicle Frequency Hopping Communication System date: 2025 words: 2195 flesch: 43 summary: Time frequency analysis is divided into linear and nonlinear methods, such as short-time Fourier transform (STFT) and Gabor transform, which are suitable for linear correlation of signal components [5]; Nonlinear distributions such as Wigner distribution (WVD) and its derivatives are used for signals that do not satisfy linear correlation conditions, with high time-frequency resolution. The number of hopping frequencies reflects the number of carrier frequency changes and is positively correlated with anti-interference performance. keywords: analysis; communication; frequency; hopping; signal; time; transform cache: fcis-30258.pdf plain text: fcis-30258.txt item: #536 of 872 id: fcis-30297 author: Cao, Minghao; Chu, Peng; Ma, Pengfei; Fang, Bo title: RT-DETR-Based Wideband Signal Detection and Modulation Classification date: 2025 words: 3365 flesch: 34 summary: Convolutional Neural Networks (CNNs), known for their excellent performance in image processing, were introduced into signal modulation recognition. Model Enhancement and Feature Fusion Techniques To further enhance the performance of deep learning models in signal modulation recognition, researchers have proposed various enhancement and optimization strategies. keywords: data; feature; learning; model; modulation; performance; recognition; signal; training cache: fcis-30297.pdf plain text: fcis-30297.txt item: #537 of 872 id: fcis-30298 author: Zhang, Hongyan; Zhang, Bing title: Design of a Logistics Management System Based on QT date: 2025 words: 3008 flesch: 51 summary: In the future, we will continue to optimize system functions, introduce embedded alternatives, transplant Qt to embedded platforms, and directly integrate modules and controllers such as cameras to form an integrated device. Logistics management system operation interface keywords: cloud; data; design; express; module; motor; system cache: fcis-30298.pdf plain text: fcis-30298.txt item: #538 of 872 id: fcis-30299 author: Zhang, Rongsen; Gu, Ailing; Hao, Yu title: Faster and More Robust GA-Lion and MM-MLP for High-Frequency Trading date: 2025 words: 4420 flesch: 52 summary: [11-12], This over-fitting problem is particularly pronounced in stock due to the noisy nature of stock price data[13].Faced with noise and volatility[14-15],a crucial challenge in modeling the stock market[16]lies in developing training methods that enable faster convergence of loss and enhancing robustness (i.e.generalization ability) of model This full connectivity can lead to over-learning of meaningless features, especially for noisy data like stock prices, which can lead to overfitting. keywords: data; frequency; learning; lion; market; mlp; model; price; stock; trading; training cache: fcis-30299.pdf plain text: fcis-30299.txt item: #539 of 872 id: fcis-30300 author: Lu, Zihan; Li, Songling; Sun, Jinzhou title: Prediction of Olympic Medal Based on Multiple Linear Regression and Logistic Regression date: 2025 words: 3107 flesch: 57 summary: A logistic regression model is used to predict countries that will win medals for the first time and to identify potential medal - winning countries. These models provide a scientific basis for countries to develop sports development strategies, help optimize resource allocation, enhance the competitiveness of Olympic medals, and have important reference value for sports event planning and national sports development. keywords: countries; country; medals; model; number; regression cache: fcis-30300.pdf plain text: fcis-30300.txt item: #540 of 872 id: fcis-30301 author: Liu, Mengting; Wang, Chongrun; Yang, Yumeng title: Research on Wine Evaluation based on Principal Component Analysis and Linear Regression date: 2025 words: 2843 flesch: 54 summary: Reducing sugar (g/l)_missing value treatment -0.5325567765308781 Soluble solids (g/l)_missing value treatment -18.115560957539337 pH value_missing value treatment 0.04658564650004515 Titratable acid (g/l)_missing value treatment 15.458154631685211 Solid - acid ratio_missing value treatment 0.038465299319630365 Dry matter content (g/100g)_missing value treatment -0.20494598449657525 Cluster mass (g)_missing value treatment 14.61675526393696 100 - grain mass (g)_missing value treatment -0.5668516090466018 Pedicel ratio (%)_missing value treatment 179.60646770357494 Juice yield (%)_missing value treatment -29.398455246731892 Prediction results 567.3488190355799 The formula of the solved model is as follows: 1 1 2 25567.349 0.007 0.56 29.398Y        Protein (mg/100g)_missing value treatment 0.5602250929878388 VC content (mg/L)_missing value treatment -0.0606280108682864 Anthocyanins (mg/100g fresh weight)_missing value treatment -0.6690405983751857 keywords: model; regression; table; treatment; value; wine cache: fcis-30301.pdf plain text: fcis-30301.txt item: #541 of 872 id: fcis-30357 author: Tang, Miao; Wen, Xin; Yang, Qiuxin; Xia, Shenhong; Luo, Yiwen title: Design of Non-contact Measurement of Alcohol Concentration Based on the Lambert-beer Law date: 2025 words: 4140 flesch: 34 summary: Block Diagram of System Figure 2. System for alcohol concentration measurement 3.2. A high-order fitting algorithm was employed to establish a mathematical model relating alcohol concentration to voltage values, followed by data processing of the measured voltage values for different alcohol concentrations. keywords: alcohol; concentration; data; figure; infrared; light; measurement; method; spectroscopy; temperature; values; voltage cache: fcis-30357.pdf plain text: fcis-30357.txt item: #542 of 872 id: fcis-30390 author: Wu, Dongze; Yang, Yonghai; Qiu, Dechuan; Li, Guangming title: TimeMixer-ME: A Dual-Memory Enhanced Architecture for Time Series Forecasting date: 2025 words: 4689 flesch: 36 summary: However, due to the unique geographical environment and climatic characteristics of Southern Xinjiang, existing precipitation forecasting models face multiple challenges in this region: Compared to the baseline TimeMixer model, it achieved a significant reduction of 2%-2.4% in MSE metrics and a remarkable improvement of 3.7%-4.2% in MAE metrics. keywords: attention; data; feature; forecasting; long; memory; model; mse; performance; precipitation; prediction; series; term; time; timemixer; weather cache: fcis-30390.pdf plain text: fcis-30390.txt item: #543 of 872 id: fcis-30391 author: Rao, Bo; Feng, Junjie; Huang, Chengxin; Chang, Junming title: Design and Optimization of Urban Stray Animal Supervision Model based on YOLOv8 and Flink date: 2025 words: 2809 flesch: 49 summary: In the scenario where this model is applied to stray animal detection, the mAP value reaches 0.767, indicating that this model has high accuracy and reliability in stray animal detection tasks. The experimental results show that the mAP value of this model in stray animal detection reaches 0.767, the F1 Score is 0.75, and the inference speed meets the requirements of real-time monitoring. keywords: accuracy; animals; bounding; data; detection; model; processing; stray; time cache: fcis-30391.pdf plain text: fcis-30391.txt item: #544 of 872 id: fcis-30392 author: Liang, Can; Sun, Liangxu; Luo, Shuaiye; Wu, Ruihao; Liu, Xingnuo title: Design of an Intelligent AGV System Based on Dynamic Navigation and Warehouse Visualization date: 2025 words: 2031 flesch: 34 summary: The proposed hybrid navigation architecture (magnetic guidance + visual SLAM correction) and digital twin visualization technology synergistically achieve high precision (±1.5 cm) and adaptability (dynamic obstacle detection rate ≥95%) for warehouse AGV systems. The communication architecture, based on MQTT protocol, publishes AGV status data (JSON format) from edge nodes to cloud topics, with the visualization platform subscribing to these topics for end-to-end transmission delays≤200 ms. Critical commands (e.g., emergency stops) are ensured via QoS2-level transmission, achieving a packet loss rate below 0.01%. keywords: agv; architecture; data; magnetic; path; planning; system; time; visualization; warehouse cache: fcis-30392.pdf plain text: fcis-30392.txt item: #545 of 872 id: fcis-30420 author: Liao, Minyue title: The Application of Intelligent Robot Numerical Control Technology in Medical Equipment Manufacturing date: 2025 words: 2985 flesch: 26 summary: The integration of intelligent robotic CNC technology with medical device manufacturing can effectively address the shortcomings of traditional manufacturing methods, aligning with the goals outlined in the 14th Five-Year Plan for the pharmaceutical industry. For the entire industry, intelligent robotic CNC technology is an inevitable trend in medical device manufacturing. keywords: cnc; device; equipment; manufacturing; medical; production; system; technology cache: fcis-30420.pdf plain text: fcis-30420.txt item: #546 of 872 id: fcis-30421 author: Wang, Zhenyong; Wang, Weiwei title: Exploration of CNC System for Polyurethane Sponge Cutting Device date: 2025 words: 3239 flesch: 37 summary: This article is based on the architecture of industrial computer+motion controller, combined with the characteristics of polyurethane sponge cutting process and the requirements of automation control, and conducts in-depth research on the CNC system of sponge cutting machine. In terms of software development, a hierarchical modular design concept is adopted to propose the upper computer software for the CNC system of sponge cutting machine, which can achieve communication function with MC1004, support the parsing, display and editing of graphic files, generate machining programs, perform machining simulation and tracking, etc. keywords: cnc; computer; control; cutting; machine; polyurethane; processing; sponge; system cache: fcis-30421.pdf plain text: fcis-30421.txt item: #547 of 872 id: fcis-30422 author: Zhang, Yaqin; Zhao, Yan; Chu, Tuanjie title: Application of Microbiological Detection Based on Computer Image Analysis date: 2025 words: 2124 flesch: 44 summary: 5. Conclusion This paper reviews microbial detection methods based on computer image analysis technology, mainly including three types of methods based on classical image processing, machine learning, and deep learning. Traditional microbial detection methods based on microscopes have some defects, and more effective methods are needed to achieve rapid and accurate analysis. keywords: analysis; detection; image; learning; machine; methods; processing cache: fcis-30422.pdf plain text: fcis-30422.txt item: #548 of 872 id: fcis-30504 author: Liu, Siqi title: Design and Optimization of Multimodal Hybrid Architectures Based on Quantum Computing date: 2025 words: 1419 flesch: 44 summary: Traditional prediction models such as AR models[1] suffer from high complexity of parameter optimization in time-series analysis, while classical classification algorithms such as SVM[2] face computational efficiency bottlenecks when dealing with high- dimensional data. In this paper, for the tasks of resource demand prediction and data classification, we propose a hybrid framework integrating classical models and quantum optimization techniques[5], which breaks through the performance boundaries of traditional methods by transforming the traditional model parameter optimization into the form of Quantum Unconstrained Binary Optimization (QUBO) and combining with the parallel searching capability of quantum computing[6]. keywords: function; optimization; quantum; qubo cache: fcis-30504.pdf plain text: fcis-30504.txt item: #549 of 872 id: fcis-30506 author: Wang, Shengxian title: Spatial Prediction of Mortality Based on Double-layer Gaussian Process Ensemble Regression Model date: 2025 words: 3325 flesch: 42 summary: [9] The achievements of scholars at home and abroad on mortality prediction models are quite abundant. As the underlying logic of actuarial science, mortality rate data provide key parameters for the rate determination of personal insurance products such as life insurance, annuity, and health insurance. keywords: data; insurance; model; mortality; population; prediction; rates cache: fcis-30506.pdf plain text: fcis-30506.txt item: #550 of 872 id: fcis-30522 author: Deng, Linlin; Lu, Xina title: Study on Small Sample Text Classification Based on Multi-Level Self-Attention and Multi-Feature Residual Fusion under Data Enhancement date: 2025 words: 4426 flesch: 53 summary: Additionally, the residual feature fusion methodology preserves critical original information while markedly improving model performance. As shown in (Fig 4), comparing the results of AEDA and EDA with the original sample data reveals that AEDA has a greater effect on improving model performance, with improvements exceeding 10% in all cases. keywords: aeda; attention; bilstm; classification; data; model; performance; sample; text; word cache: fcis-30522.pdf plain text: fcis-30522.txt item: #551 of 872 id: fcis-30523 author: Zheng, Haohong title: Leveraging Big Data and AI for Personalized Healthcare Solutions in Smart Cities date: 2025 words: 3080 flesch: 43 summary: This research design explains how health data is collected, processed, and analyzed within the setting of a smart city for personalized healthcare solutions. The outcome showed how the integration of health data from different sources could provide actionable insights at both individual and provider levels. keywords: cities; data; diseases; health; healthcare; management; research cache: fcis-30523.pdf plain text: fcis-30523.txt item: #552 of 872 id: fcis-30524 author: Wang, Haotian; Gan, Zhongxue title: A Method for Redirecting Humanoid Robots Based on Segmented Geometric Inverse Kinematics date: 2025 words: 3797 flesch: 46 summary: Summary In this study, a visual dexterous teleoperation method for robot upper limb based on human skeleton tree reorientation is proposed. This study provides a new research idea and implementation way for human-robot collaboration in robot upper limb teleoperation. keywords: algorithm; human; motion; node; robot; skeleton; smpl; system; teleoperation; tree cache: fcis-30524.pdf plain text: fcis-30524.txt item: #553 of 872 id: fcis-30581 author: Wei, Xuanning; Zhou, Jianhan title: Multimodal Road Traffic Detection Algorithm based on Improved YOLOv8 date: 2025 words: 4680 flesch: 42 summary: And target detection, as its important branch, has received attention and favour from many researchers. Target detection as one of the core in the field of computer vision is divided into two categories: detection based on traditional methods and detection based on deep learning. keywords: attention; branch; channel; detection; feature; fusion; information; infrared; map; model; network; target cache: fcis-30581.pdf plain text: fcis-30581.txt item: #554 of 872 id: fcis-30583 author: Xie, Liyuan title: Design and Implementation of Rural Culture and Tourism Software based on Wechat Small Program: -- Take the "Yushang Rice Township" Mini Program as an Example date: 2025 words: 3391 flesch: 44 summary: Abstract: With the advancement of the rural revitalization strategy and the rapid development of mobile internet technology, as well as the application and advantages of Wechat Mini Programs in rural cultural tourism. This project iteratively upgraded and designed a shared interactive platform for rural cultural tourism in the post- pandemic era, based on the Rice Fragrance Town Wechat mini-program originally located in Yong'an Village, Yuhang District, Hangzhou City, Zhejiang Province, China. keywords: app; data; design; information; mini; pages; rural; system; table; tourism; user; wechat cache: fcis-30583.pdf plain text: fcis-30583.txt item: #555 of 872 id: fcis-30615 author: Zhang, Xinyu; Li, Yaqi title: Cotton Pest Detection Method based on Improved YOLOv8 date: 2025 words: 3382 flesch: 44 summary: The original YOLOv8n model fuses pyramid features through simple concatenation or addition, which inadequately exploits correlations between multi-scale feature maps, leaving room for improvement in detecting cotton pests and diseases with inherent scale variations. The head network generates feature maps corresponding to the number of target categories. keywords: attention; channel; conv; cotton; detection; disease; feature; fusion; leaf; map; model; module; scale cache: fcis-30615.pdf plain text: fcis-30615.txt item: #556 of 872 id: fcis-30616 author: Wang, Nanjun title: Research on the Use of Artificial Intelligence in Subject Services of University Libraries date: 2025 words: 2947 flesch: 34 summary: Ultimately, it emphasizes that library subject services need continuous innovation to adapt to the changes brought by AI, and better serve the construction of education and intelligent education systems. In addition, libraries should strengthen in-depth cooperation with the information technology field and actively explore how to deeply integrate AI with library subject services to achieve a more precise and efficient service model. keywords: data; libraries; library; services; subject; university cache: fcis-30616.pdf plain text: fcis-30616.txt item: #557 of 872 id: fcis-30617 author: Song, Qiao; Song, Zengren title: Improvement of Data Cleaning and Quality Assessment Methods Under Big Data Environment date: 2025 words: 4061 flesch: 51 summary: Missing data will affect the integrity and accuracy of data analysis. Data Errors Data errors are manifested as data values that do not match the actual situation. keywords: analysis; big; cleaning; data; duplicate; example; method; quality; value cache: fcis-30617.pdf plain text: fcis-30617.txt item: #558 of 872 id: fcis-30618 author: Liu , Yibo title: Discussion and Optimization of AES and SM4 Encryption Algorithms date: 2025 words: 4282 flesch: 49 summary: This aims to address the present demands for data encryption and decryption at both high speeds and security levels. Fast Dual-encryption Technique based on the AES and SM4 Algorithms AES encryption algorithm, as a widely used symmetric encryption technology, has been generally recognized by the industry and is widely used for data encryption and protection. keywords: aes; algorithm; data; encryption; hybrid; key; security; sm4 cache: fcis-30618.pdf plain text: fcis-30618.txt item: #559 of 872 id: fcis-30619 author: Zhang, Yulin title: Application of Composite Kernel Function in Gaussian Process Prediction date: 2025 words: 1624 flesch: 43 summary: Different kernel functions can be selected based on the characteristics of the data to improve model performance. House price prediction performance under different kernel functions Figure 1 shows the housing price prediction performance under different kernel functions. keywords: data; functions; gaussian; kernel cache: fcis-30619.pdf plain text: fcis-30619.txt item: #560 of 872 id: fcis-30620 author: Yu, Nuolin title: Research on Distributed Photovoltaic Data Prediction Based on Deep Learning Method date: 2025 words: 3456 flesch: 50 summary: Based on the above analysis, this paper focuses on the key technical problems of distributed photovoltaic data prediction, and proposes a prediction method that combines meteorological historical data and long-term and short-term memory network (LSTM). It aims to improve the accuracy and reliability of distributed photovoltaic power prediction through refined meteorological data classification and deep feature mining, and provide theoretical support and technical reference for the efficient operation of power system and the scientific planning of distributed energy. keywords: data; lstm; meteorological; model; photovoltaic; power; prediction; weather cache: fcis-30620.pdf plain text: fcis-30620.txt item: #561 of 872 id: fcis-30621 author: Chen, Xudong title: A Blockchain-based Trust Management Model for IoV date: 2025 words: 3941 flesch: 53 summary: China Abstract: In this paper, we design a blockchain and social information-driven trust management model for the Internet of Vehicles (IoV), which effectively solves the problems of sparse node interactions, data dynamics, and malicious attacks faced by trust management in the IoV environment. Trust management in the Social Internet of Things has been studied by many researchers for a long time. keywords: blockchain; iot; management; model; nodes; system; trust; value cache: fcis-30621.pdf plain text: fcis-30621.txt item: #562 of 872 id: fcis-30622 author: Wang, Shasha; Zhao, Xiaoyi title: Deep Learning in Tongue Diagnosis for Traditional Chinese Medicine: A Review date: 2025 words: 4096 flesch: 36 summary: First, collect tongue diagnosis images and perform preprocessing, including color correction and data augmentation. [36] conducted image quality assessment on tongue diagnosis images, followed by color correction and tongue segmentation. keywords: accuracy; classification; diagnosis; image; learning; medicine; model; segmentation; tcm; tongue cache: fcis-30622.pdf plain text: fcis-30622.txt item: #563 of 872 id: fcis-30624 author: Zhong, Yingjie title: Identification of Robot Dynamic Parameters Based on BP Neural Network date: 2025 words: 4043 flesch: 53 summary: Furthermore, it enhances the efficiency and accuracy of dynamic parameter identification. This paper aims to investigate the problem of dynamic parameter identification using neural networks. keywords: identification; joint; model; network; neural; parameter;   cache: fcis-30624.pdf plain text: fcis-30624.txt item: #564 of 872 id: fcis-30625 author: Dai, Yingdong; Jie, Meng; Zhang, Yiming title: STM32-Based Piezoelectric Ceramic Control System date: 2025 words: 4099 flesch: 53 summary: The use of microcontroller main controller and other scale integrated components to design the drive circuit can achieve fast and stable control and high degree of automation, with automatic fault detection function to increase the anti- interference ability to achieve high power, low power consumption of high dynamic response output [7][8]. System Output Waveform 6. keywords: chip; circuit; control; design; frequency; output; piezoelectric; power; system; voltage; waveform cache: fcis-30625.pdf plain text: fcis-30625.txt item: #565 of 872 id: fcis-30626 author: Xie, Minghui; Ren, Hongwei title: Research on UAV Formation Control under Deception Attacks date: 2025 words: 7159 flesch: 33 summary: This paper systematically reviews the current research status of UAV formation control under deception attacks, providing an in-depth analysis from multiple dimensions, including research background, technical challenges, control methods, and security defenses. First, the development history and key technologies of UAV formation control are introduced. keywords: adaptive; attacks; communication; consensus; control; deception; et al; formation; formation control; ieee; method; multi; research; security; systems; technology; uav; uav formation; uavs cache: fcis-30626.pdf plain text: fcis-30626.txt item: #566 of 872 id: fcis-30627 author: Cheng, Qiyang; Wang, Xinyu; Zheng, Chengwei; Hou, Yunlong; Li, Zhaoyu; Feng, Yingqiao title: Algorithm Design and Experimental Research on Achievement Analysis of Output Oriented Course Objectives, Using Digital “Signal Processing A” as a Case Study date: 2025 words: 3785 flesch: 39 summary: The target score for student courses is , where, iA is the specific proportion of students in the assessment project, combined with the corresponding score of the course objectives, the target score of the student's course is  Score distribution of course assessment items in each course objective Assessment items Course objectives 1 Course objectives 2 Course objectives 3 final exam 40 40 20 Chapter Test 50 50 0 Homework situation 30 30 40 Performance in Hall 20 30 50 Expansion training 3 3 4 Let iScore be the corresponding score for course objective I, jSco is the actual score of the student's course objectives. keywords: achievement; assessment; course; goal; objectives; performance; students; system; teaching cache: fcis-30627.pdf plain text: fcis-30627.txt item: #567 of 872 id: fcis-30629 author: Wang, Guogang; Sun, Qilong title: Constrained Manipulator Force Position Hybrid Control Based on Fuzzy Neural Network date: 2025 words: 3976 flesch: 64 summary: In the formula, 1 1 1 ( ) Ψ( ) 1 L q q q          Therefore, the dynamic equation of a constrained two- degree-of-freedom manipulator is: T 1 1 1 1 1 1 1 1 1 1 1( ) ( , ) ( ) ( ) ( )M q q C q q q G q f q cos - 2 π q q q π q q q q π q   (27) 1q 2q 2m 1m 1l 1l 2x 1x Fig 1. keywords: t t;   cache: fcis-30629.pdf plain text: fcis-30629.txt item: #568 of 872 id: fcis-30659 author: Huang, Youpeng; Lv, Yong title: Research on Network Attack Early Warning and Defense Strategies for Blockchain Networks date: 2025 words: 4472 flesch: 39 summary: This research aims to explore the early warning and defense strategies for network attacks in blockchain systems. For example, PoS reduces the energy consumption of mining while maintaining network security. keywords: attacks; blockchain; defense; mechanisms; network; security; strategies; systems; vulnerabilities cache: fcis-30659.pdf plain text: fcis-30659.txt item: #569 of 872 id: fcis-30660 author: Wang, Jian; Li, Shuaihui; Zeng, Dandan; Yan, Bo; Chen, Hao title: Algorithm of Non-LTE Infrared Radiation in Atmosphere and Its Application date: 2025 words: 8517 flesch: 53 summary: Compared to vibrational energy levels, rotational energy levels require significantly fewer collisions to maintain an equilibrium distribution. Processes 1-2 represent thermal collisions between neutral molecules and CO2, while processes 3-8 involve vibrational energy levels of CO2 in V-V transitions. keywords: altitude; atmospheric; band; energy; energy level; equilibrium; levels; non; radiance; radiation; vibrational cache: fcis-30660.pdf plain text: fcis-30660.txt item: #570 of 872 id: fcis-30661 author: Lu, Xing title: Research on the Performance of Cosmetics Packaging Materials under the Background of Green Transformation date: 2025 words: 2678 flesch: 25 summary: 171189210@qq.com Abstract: With the acceleration of global green transformation, the cosmetics industry is facing an urgent need for sustainable upgrading of packaging materials. Introduction With the continuous expansion of the global cosmetics market, the safety and sustainability of packaging materials have become the focus of industry attention. keywords: compatibility; contents; cosmetics; detection; materials; migration; packaging; temperature; testing cache: fcis-30661.pdf plain text: fcis-30661.txt item: #571 of 872 id: fcis-30665 author: Xiang, Shu title: Study on Parameter Estimation of Load-Sharing Parallel Systems under Log-Logistic Component Lifetimes date: 2025 words: 4278 flesch: 59 summary:     1 1 ln ln 2 0 ( , ) 1 j n n j ij j ij β i= i=j j j ij α tn = l + n k j j ij i= j= l keywords: estimation; j j; k j; α α;   cache: fcis-30665.pdf plain text: fcis-30665.txt item: #572 of 872 id: fcis-30671 author: Tao, Ziliang; Sun , Zhuo; Jin, Fanqing title: Research on Control Strategy of Full-Bridge LLC date: 2025 words: 1758 flesch: 48 summary: Based on the above research, this paper designs a control strategy based on linear active disturbance rejection control PSM+PFM hybrid modulation for LLC resonant converter. Small Signal Modeling Small-signal modeling of LLC resonant converter is the basis for analyzing closed-loop control and parameter design of the converter. keywords: control; converter; llc; mode; modulation; resonant cache: fcis-30671.pdf plain text: fcis-30671.txt item: #573 of 872 id: fcis-30674 author: Wang, Min title: An Ensemble Multi-Model Voting Method for Adapting to Concept Drift date: 2025 words: 3246 flesch: 52 summary: (1) Average real-time accuracy is a measure of the average level of model performance over the entire time course, defined as: ∑ (9) where represents the accuracy of the model at time node . Subsequently, the output results of multiple base models are voted to get the final result, which improves the robustness of the model. keywords: average; base; concept; data; drift; layer; learning; model; results; time cache: fcis-30674.pdf plain text: fcis-30674.txt item: #574 of 872 id: fcis-30675 author: Wang, Xiaotao; Zhang, Hongyan; Liu, Huijie; Sun, Renjie; Zhang, Haitao title: Research on Navigation of Smart Robots in Gerocomium Based on DWA date: 2025 words: 4100 flesch: 53 summary: Introduction With the increasing severity of global aging, the application of intelligent robots in gerocomiums in the elderly care market is becoming more and more widespread. There have been repeated dangerous accidents where intelligent robots in gerocomiums collide with the elderly. keywords: camera; distance; dwa; face; figure; gerocomium; lidar; navigation; path; robot; safety cache: fcis-30675.pdf plain text: fcis-30675.txt item: #575 of 872 id: fcis-30676 author: Sun, Zhuo; Tao, Ziliang; Jin, Fanqing title: Research on EPS Modulation Strategy of DAB Converter with Low Surge Current date: 2025 words: 3129 flesch: 53 summary: The maximum current stress expression of extended phase shift modulation is: 1 2 1 0 1 max 1 2 1 , 1 0 1 (5) 2.3. The output current of single phase shift (SPS) modulation is obtained in the same way. keywords: control; current; eps; modulation; phase; power; shift cache: fcis-30676.pdf plain text: fcis-30676.txt item: #576 of 872 id: fcis-30726 author: Miao, Yingying; Zi, Yonghui; Shen, Xichong title: Research on the Teaching Reform of "Java Web Technology" for Engineering Education Certification date: 2025 words: 3398 flesch: 35 summary: This paper is oriented to the concept of engineering education, discusses the status quo of teaching reform of Java Web courses, points out the problems of teaching Java Web technology at the present stage, and then gives the reform method of teaching Java Web technology for engineering education certification. Through the teaching effect comparison experiment, it can be seen that the implementation of engineering education certification-oriented “Java Web technology” course effect has a significant improvement over the results of the students who did not implement it, and the number of students who scored more than 80 points is significantly higher than the number of students who did not implement it; Finally, this paper re-emphasizes the significance of the teaching reform of “Java Web Technology” for engineering education certification. keywords: course; education; engineering; java; students; teaching; technology; web cache: fcis-30726.pdf plain text: fcis-30726.txt item: #577 of 872 id: fcis-30730 author: Wang, Jie title: Penelitian Tentang Kontrol Heading Berdasarkan PID Neural Fuzzy date: 2025 words: 1729 flesch: 63 summary: Summary In this article, a comparative study of PID, fuzzy PID and fuzzy neural PID control methods is carried out to address the problem of heading control of a kelp harvesting vessel. Firstly, fuzzy logic and neural network technology are combined, and secondly, fuzzy PID, fuzzy neural PID control strategy model and heading control model are designed through Simulink. keywords: controller; fuzzy; k k; layer; pid cache: fcis-30730.pdf plain text: fcis-30730.txt item: #578 of 872 id: fcis-30832 author: Chen, Xianyan title: An Electric Vehicle Optimal Charging Path Planning based on an Improved A* Algorithm date: 2025 words: 6308 flesch: 45 summary: The efficiency of path planning algorithms can be reflected by the ratio of path length to planning time, which indicates the algorithm's ability to plan paths per unit of time. To improve the efficiency of electric vehicle promotion and reduce operating costs, it is necessary to consider path planning strategies to plan reasonable charging routes that meet the goal of timely charging and range extension. keywords: adaptation strategy; algorithm; charging; function; goal; node; path; path planning; path search; search; strategy cache: fcis-30832.pdf plain text: fcis-30832.txt item: #579 of 872 id: fcis-30916 author: Shang, Yaqin; Zhang, Xiaolin; Cao, Yang title: Research on the Front-End Architecture Design and Visualization Implementation of Agricultural Internet of Things Based on Vue 3 date: 2025 words: 3317 flesch: 33 summary: DeviceStore is responsible for obtaining device data and updating the status, driving the real- time refresh of the monitoring interface. (3) ECharts data visualization keywords: architecture; data; design; end; management; platform; state; status; system; time; vue cache: fcis-30916.pdf plain text: fcis-30916.txt item: #580 of 872 id: fcis-30943 author: Dong, Fanjing title: A Review of Business Data Security Based on Differential Privacy Protection date: 2025 words: 3981 flesch: 42 summary: Machine Learning and Model Training Differential privacy techniques in the field of machine learning, on the other hand, protect data privacy by adding noise to the training process, such as the differential privacy optimized gradient descent algorithm (DP-SGD), which adds noise to the gradient update to protect the privacy of the training data while maintaining the performance and utility of the model. Introduction With the rapid development of artificial intelligence, a large amount of commercial information is becoming increasingly transparent in the data network, especially in the booming e-commerce, it is particularly urgent and crucial to protect commercial privacy data and prevent privacy invasion, which is largely related to the survival and development of related enterprises. keywords: analysis; data; differential; differential privacy; learning; noise; privacy; protection; research; techniques cache: fcis-30943.pdf plain text: fcis-30943.txt item: #581 of 872 id: fcis-30952 author: Han, Shuyang title: Quality Control in Umbrella Manufacturing Based on Object Detection: Current Applications and Challenges date: 2025 words: 1962 flesch: 21 summary: Abstract: With the increasing complexity of umbrella manufacturing processes, traditional quality inspection methods are facing significant challenges in terms of accuracy and efficiency. This paper systematically reviews the current applications and future trends of object detection technologies in addressing quality control challenges in umbrella manufacturing, such as the heterogeneous integration of multiple components and dynamic deformation of flexible materials. keywords: control; detection; inspection; manufacturing; methods; object; quality; umbrella cache: fcis-30952.pdf plain text: fcis-30952.txt item: #582 of 872 id: fcis-30954 author: Shen, Teqiao; Rong, Jialei title: Research on Smart Cultural Tourism Based on Virtual Reality Technology date: 2025 words: 2740 flesch: 30 summary: Current Applications of Virtual Reality Technology The current application of virtual reality technology in smart cultural tourism has presented diverse scenarios and innovative practices. Analysis of the Advantages and Disadvantages of the Technical Solution The technical solutions of virtual reality technology in smart cultural tourism not only show significant advantages 34 but also have limitations that need to be urgently broken through. keywords: data; development; heritage; reality; smart; technology; tourism cache: fcis-30954.pdf plain text: fcis-30954.txt item: #583 of 872 id: fcis-30955 author: Yang, Lulu; Ma, Wenhao; Zhou, Jiajia; Wen , Rongchao title: The Control System of the Full-automatic Dryer Based on PLC date: 2025 words: 1931 flesch: 61 summary: Standard mode program diagram 38 Figure 6. This paper designs a set of fully automatic dryer control system based on Siemens PLC. keywords: control; figure; mode; operation; plc; system cache: fcis-30955.pdf plain text: fcis-30955.txt item: #584 of 872 id: fcis-30980 author: Wu, Zuxian; Hou, Zhesheng title: Design of Straw Moisture Detector based on AC Impedance Method date: 2025 words: 2310 flesch: 57 summary: At present, corn straw moisture detection methods include rapid drying method, near-infrared spectroscopy, microwave attenuation method, capacitance method and resistance method Corn straw moisture content detection device 47 2.2. keywords: circuit; content; impedance; moisture; straw; temperature cache: fcis-30980.pdf plain text: fcis-30980.txt item: #585 of 872 id: fcis-30981 author: Wang, Huayu title: Online Identification of Low-Speed Misfit Driving Behavior based on Fuzzy Comprehensive Evaluation Method and XGBoost Algorithm date: 2025 words: 4386 flesch: 49 summary: In Figures 6, 7, and 8, the left graph shows the changes in vehicle speed, rear vehicle speed, and distance from the vehicle in front, and the right graph shows the absolute value of the speed difference between vehicles on the road during the period from the appearance of the vehicle to its departure. To date, most studies have focused on vehicle speed as the primary indicator of low-speed behavior and have emphasized mitigation strategies after bottlenecks form. keywords: behavior; data; driving; evaluation; fuzzy; misfit; model; samples; speed; traffic; vehicle cache: fcis-30981.pdf plain text: fcis-30981.txt item: #586 of 872 id: fcis-30988 author: Ren , Jie; Hao, Weijia title: Research on Airport Traffic Situation Based on Multi-Source Data date: 2025 words: 1868 flesch: 36 summary: Airport operations are influenced by multiple factors, including flight data (e.g., flight numbers, schedules, delays), meteorological data (e.g., weather conditions, wind speed, visibility), ground traffic data (e.g., vehicle flow, road congestion), and other related factors (e.g., facility status, staffing) The results demonstrate that the intelligent prediction method based on multi-source data fusion significantly improves the accuracy and reliability of airport operation forecasting, providing a scientific basis for airport management and enhancing operational efficiency and service quality. keywords: airport; data; delays; flight; fusion; model; optimization; prediction; traffic cache: fcis-30988.pdf plain text: fcis-30988.txt item: #587 of 872 id: fcis-30996 author: Wang, Saijie; He, Dongyang; Shan, Yufei; Li, Hongjia title: Olympic Medal Count Prediction Model for Various Countries based on LSTM and Supervised Machine Learning date: 2025 words: 2343 flesch: 55 summary: 4. Results Given that our built-in model is a regression supervised learning model, we use the Root Mean Square Error (RMSE), Mean Square Error (MSE), and R-squared (R2) goodness-of- fit to evaluate the model's prediction results. Through the Random Forest model, we can deeply explore the potential relationships between features and medal counts, thereby effectively predicting the number of medals for each country. keywords: country; data; feature; learning; lstm; medal; model cache: fcis-30996.pdf plain text: fcis-30996.txt item: #588 of 872 id: fcis-30998 author: Cui, Haiyang; Huang, Yingying; Lan, Keyun; Yue, Xianyu; He, Yujia; Yan, Wanglong title: A Flight Conflict Detection Method for eVTOLs date: 2025 words: 4217 flesch: 53 summary: This model also incorporates the output results of the flight trend detection module, significantly enhancing the efficiency and accuracy of flight conflict detection. This method not only improves the accuracy of flight conflict detection but also provides strong technical support for flight control work. keywords: ads; aircraft; conflict; data; detection; evtol; flight; svm; vector cache: fcis-30998.pdf plain text: fcis-30998.txt item: #589 of 872 id: fcis-30999 author: Jiang, Jinyi title: Algorithm Optimization and Performance Enhancement in Computer Science date: 2025 words: 1971 flesch: 39 summary: Jinyi0208@outlook.com Abstract: In the broad field of computer science, algorithm optimization is regarded as the cornerstone of improving system performance. This paper will deeply discuss the method of algorithm optimization and how it can help significantly improve the computer performance in practical applications, Process data more efficiently, which prompts all work to improve efficiency accordingly. keywords: algorithm; data; optimization; performance; science; time cache: fcis-30999.pdf plain text: fcis-30999.txt item: #590 of 872 id: fcis-31000 author: Zhang, Jiayao; Huang, Yan title: Research and Implementation of Enterprise Intelligent Operation and Management System date: 2025 words: 2125 flesch: 19 summary: The third stage pertains to cross-system data application, such as integration with project management systems (ERP, PRP), design management systems (EPMS), science and technology management systems, and financial management systems. In recent years, the rapid development of big data, cloud computing, and artificial intelligence has provided technological support for the intelligent upgrading of enterprise management systems. keywords: business; customer; data; efficiency; enterprise; management; operation; systems cache: fcis-31000.pdf plain text: fcis-31000.txt item: #591 of 872 id: fcis-31002 author: Xu , Wentao title: Optimizing the Integration of Enterprise Data Warehouses and Large Language Models date: 2025 words: 2662 flesch: 34 summary: Therefore, data warehouse technology urgently needs to break through the dynamic optimization mechanism of multi- dimensional indexing, the low-cost intelligent decision- making model, and the elastic architecture that supports heterogeneous data fusion, laying the foundation for the subsequent integration with large language model technology. However, the rapid development of large language model technology provides a new path for the intelligence of data processing. keywords: analysis; data; enterprise; language; model; processing; warehouses cache: fcis-31002.pdf plain text: fcis-31002.txt item: #592 of 872 id: fcis-31019 author: Zhu, Qiqi; Kong, Lei title: Research on Road Construction and Maintenance Technology of Open-Pit Mines date: 2025 words: 2946 flesch: 55 summary: This paper systematically analyzes the characteristics and classification of open-pit mine roads, discusses the key technologies of road construction, including subgrade treatment, pavement structure design, drainage system setting, etc., and elaborates the technical points and management measures of road maintenance. Seasonal Maintenance Priorities The focus of road maintenance varies in different seasons: 1. keywords: construction; design; maintenance; mines; mining; pavement; pit; road; technology cache: fcis-31019.pdf plain text: fcis-31019.txt item: #593 of 872 id: fcis-31029 author: Ye, Nanjun title: Elasticsearch for Complex Data Association Analysis: Modeling, Aggregation, and Optimization Techniques date: 2025 words: 4049 flesch: 25 summary: 3. Background and Preliminaries To establish a foundation for our methodology, this section introduces core concepts in data association analysis and Elasticsearch’s architectural features that enable efficient relationship discovery. China Abstract: This study proposes a comprehensive methodology for complex data association analysis using Elasticsearch (ES), addressing the challenges of modeling, querying, and optimizing large-scale relational datasets. keywords: aggregation; analysis; association; data; datasets; elasticsearch; graph; methodology; metrics; performance; query; relationships; systems cache: fcis-31029.pdf plain text: fcis-31029.txt item: #594 of 872 id: fcis-31030 author: Hong, Huihui; Chen, Zuozi title: Wall Climbing Robot for High-Altitude Steel Frame Inspection date: 2025 words: 1784 flesch: 45 summary: References [1] Schmidt, D., & Berns, K. Climbing robots for inspection and maintenance of large structures—A survey of design aspects and technologies. 2. Working Principle and Functions of Robots keywords: adsorption; control; detection; module; robot; sensor; system cache: fcis-31030.pdf plain text: fcis-31030.txt item: #595 of 872 id: fcis-31117 author: Zhao, Yunwei; Zeng, Wen; Peng, Lingxing; Zhao, Pengtao; Li, Dexuan title: Application of Intrinsic Time-Scale Decomposition in Ground Penetrating Radar Data Processing date: 2025 words: 2922 flesch: 46 summary: The ITD algorithm employs a single-wave analysis, which is capable of real-time processing of signals 17 and provides an efficient and accurate time-frequency analysis method in the field of signal analysis. The ITD algorithm uses a single-wave analysis method to process the signal in real time, providing an efficient and accurate time- frequency analysis method for signal analysis. keywords: data; decomposition; ground; radar; scale; signal; time cache: fcis-31117.pdf plain text: fcis-31117.txt item: #596 of 872 id: fcis-31123 author: Wen , Jiachao; Liang, Zexuan; Yan , Haipeng; Zheng, Jimeng; Guo, Jiarui ; Wang, Yaxin; Duan, Yale title: Ecological Floating Island Multi-specification and Multi-sample Delivery Drone date: 2025 words: 3306 flesch: 48 summary: Ecological floating island transportation UAV transportation cycle diagram The UAV is mainly used for the transportation of ecological floating island samples. keywords: block; box; clamping; drone; fig; flight; mechanism; sample; self; transportation; uav cache: fcis-31123.pdf plain text: fcis-31123.txt item: #597 of 872 id: fcis-31125 author: Tu, Qiuxiang; Dong, Changzhou; Guo, Shiyu; Liu, Sijing; Li, Ying title: Trust Anchors in the Sharing Economy: A Study on Trust and Usage Intention in Shijiazhuang’s AI-Era Sharing Economy date: 2025 words: 4560 flesch: 29 summary: Oversimplified Cultural Framing: 70% of trust models treat Confucian societies as monolithic, neglecting intra- regional variations (e.g., Shijiazhuang vs. Shenzhen) AI-driven dynamic trust scoring: Develop machine learning models that adjust user trust scores in real-time based on behavioral data (e.g., transaction consistency) and social parameters (e.g., community reputation), tested via RCTs in counties like Luquan. keywords: analysis; blockchain; community; dynamic; platform; research; risk; sharing; shijiazhuang; systems; tier; transparency; trust; usage; user cache: fcis-31125.pdf plain text: fcis-31125.txt item: #598 of 872 id: fcis-31208 author: Ye, Minyi; Wu, Lanqing; Zhu, Guanquan; Jiang , Jiaguo title: Research on Machine Learning Optimization Algorithm Based on QUBO Model date: 2025 words: 5354 flesch: 46 summary: QUBO model can discretize continuous variables (including parameters such as weights and bias) in AR, SVM, CNN and other models in machine learning into binary variables, so as to better deal with nonlinear relationships and reduce the computational complexity in the training process. Flow chart of QUBO model solved by simulated annealing For the parameters in the simulated annealing solver in the Kaiwu SDK, we set them as follows: Select the initial temperature and the end temperature , and select the appropriate cooling coefficient during the annealing process, so that the iterative depth of each temperature in the annealing process does not exceed 100. keywords: annealing; binary; classification; data; iris; model; qubo; qubo model; value cache: fcis-31208.pdf plain text: fcis-31208.txt item: #599 of 872 id: fcis-31216 author: Gao, Jiayu; Suo, Yijia; Xing, Wanyun title: Prediction of Cybercrime and Policy Evaluation Using a Combination of PageRank and ARIMA-DID Algorithms date: 2025 words: 3369 flesch: 49 summary: Analysis of the Effects of Policy Implementation To test the effectiveness of countries' cybersecurity policies, it is not possible to simply compare cybercrime rates before and after policy implementation, as fluctuations in crime rates are affected by a variety of factors. In predicting cybercrime rates, the smoothness of the data is tested, the non-smooth data is differenced to make it smooth, and then the model parameters (p,d,q) are determined by the AIC and BIC methods. keywords: countries; cybercrime; cybersecurity; model; pagerank; paper; policy; rate; risk cache: fcis-31216.pdf plain text: fcis-31216.txt item: #600 of 872 id: fcis-31236 author: Xie, Huipeng; Xu, Zhengbin; Lv, Jiajun; Dai , Yujia title: Study on Urban Flood Risk Assessment and Precipitation Prediction Based on SA-Informer Model date: 2025 words: 3877 flesch: 38 summary: The model provides data support and theoretical cornerstone for the construction of precipitation prediction models. First, this study constructs a risk assessment system based on the P-S-R model integrating heterogeneous data from multiple sources, and analyzes the impacts of the pressure subsystem and response subsystem indicators on the coupling degree of coordination through the combination of the AHP-CRITIC assignment and the improvement of the ternary coupling degree of coordination model, combined with the stepwise regression model, which confirms that the heavy precipitation as a core driver is significantly related to the increase in risk level, and lays the foundation for the construction of the prediction model. keywords: assessment; coordination; coupling; degree; flood; informer; model; precipitation; prediction; risk cache: fcis-31236.pdf plain text: fcis-31236.txt item: #601 of 872 id: fcis-31241 author: Ye, Sen; Sun, Mingge; Li, Jian; Huang, Dongxuan; Chai, Jiaxuan title: A Comparative Study on Edge Detection Algorithms for Automotive Lighting Systems date: 2025 words: 2262 flesch: 33 summary: LOG Operator (Marr-Hildreth Operator) Detection Principle and Applications Marr-Hildreth edge detection is a classical and important method for image edge detection. Edge detection methods in image processing enable efficient and precise extraction of light pattern contours, providing technical support for automated inspection systems. keywords: algorithm; detection; edge; gaussian; image; inspection; method; operator cache: fcis-31241.pdf plain text: fcis-31241.txt item: #602 of 872 id: fcis-31242 author: Wang, Guogang; Sun, Hongwei; Xie, Shouliang; Chen, Xu; Feng, Zichao title: Multi-Strategy Improved Petal Kingfisher Algorithm for Robot Path Planning date: 2025 words: 3738 flesch: 47 summary: Analysis of Experimental Results From Figure 1, it can be seen that the improved algorithm in this paper in the single-peak function, multi-peak function and composite function under the convergence speed and are faster than other algorithms, in the single-peak function test, IPKO algorithm convergence speed is faster than the other optimization algorithms, can be in the early iteration to quickly find the location of the optimal solution, in the multi- peak function test, the IPKO algorithm has a stronger convergence accuracy and the ability to jump out of the local optimal solution, composite function In the multi-peak function test, IPKO algorithm has stronger convergence accuracy and ability to jump out of the local optimal solution, and the convergence curve of IPKO algorithm is significantly higher than PKO algorithm in the middle and late stages of the test, which indicates that IPKO algorithm is better than other optimization algorithms in terms of convergence speed, convergence accuracy, and optimization searching ability, and it is more suitable for the ability of complex optimization problems and better robustness. At the same time calculated the number of turns in the path planning algorithm, path length and convergence time as the key indicators of the 67 performance of each algorithm, these indicators not only take into account the speed of the algorithm to reach the optimal position, but also measures the degree of optimization of the algorithm and the practicality of the planning, in order to ensure that the algorithm in the path planning of the fairness, the maximum number of iterations are set to 500, the number of populations are 30. keywords: algorithm; convergence; function; kingfisher; optimization; path; pko; planning; robot; search cache: fcis-31242.pdf plain text: fcis-31242.txt item: #603 of 872 id: fcis-31243 author: Shao, Wen; Qin, Yihong; Ji , Zongyao title: Research on Vehicle-Road Collaboration and Autonomous Driving Algorithms date: 2025 words: 2275 flesch: 34 summary: 3. Data Fusion Architecture The data fusion architecture of vehicle road collaboration and autonomous driving systems revolves around data collection, transmission, and processing. Under the same communication quality requirements, the number of RSUs deployed can be reduced by 20%, effectively improving the economy and practicality of network deployment and providing a scientific network deployment solution for the large-scale implementation of vehicle road collaboration systems. keywords: communication; data; driving; fusion; road; system; traffic; v2x; vehicle cache: fcis-31243.pdf plain text: fcis-31243.txt item: #604 of 872 id: fcis-31244 author: Chai, Jiaxuan; Sun, Mingge; Huang, Dongxuan; Ye, Sen title: Lightweight Dynamic Gesture Recognition based on shufflenetv2-Mamba Hybrid Architecture date: 2025 words: 3897 flesch: 44 summary: Mingge Sun Abstract: Dynamic gesture recognition has important application value in human-computer interaction of mobile terminal, but the existing methods generally face the problems of high computational complexity and insufficient time sequence modeling ability. In dynamic gesture recognition, transformer can process the sequence of video frames and analyze the continuity and local details of gesture actions through attention mechanism. keywords: convolution; data; dynamic; feature; gesture; mamba; model; network; recognition; sequence; shufflenetv2; time cache: fcis-31244.pdf plain text: fcis-31244.txt item: #605 of 872 id: fcis-31253 author: Miao, Kunlin; Wang, Zhaobo; Zhao, Jinchao title: Design and Implementation of an IoT-Based Smart Greenhouse System date: 2025 words: 2349 flesch: 39 summary: China Abstract: The integration of Internet of Things (IoT) technology into greenhouse systems effectively addresses prevalent challenges such as temperature and humidity imbalances, as well as insufficient lighting in greenhouse management. After analyzing sensor data, including temperature and humidity, it links with steaming and fumigation equipment for automated pest control, thereby reducing the use of chemical agents and avoiding unnecessary harm to humans. keywords: control; data; greenhouse; humidity; level; light; module; sensor; system; temperature cache: fcis-31253.pdf plain text: fcis-31253.txt item: #606 of 872 id: fcis-31255 author: Wang, Bowen; Guan, Xuemei title: Research on Parallel Testing Technology of MCU Chips Based on ATE date: 2025 words: 2815 flesch: 51 summary: This paper introduces the implementation methods of parallel testing technology based on ATE, such as the hardware architecture design of the test system, the optimization strategy of the test process, and the processing and analysis methods of test data. In order to achieve real-time collection and processing of test data, corresponding data collection points are set in the test program. keywords: chips; data; mcu; production; test; testing; time cache: fcis-31255.pdf plain text: fcis-31255.txt item: #607 of 872 id: fcis-31256 author: Qiu, Dechuan; Shan, Yongfu; Wang, Yingchao; Qin, Lihao; Li, Na title: Lightweight Recognition Method for Korla Pear Based on NanoDet-Plus date: 2025 words: 2580 flesch: 38 summary: Specifically, mAP@0.5 assesses average precision based on predictions overlapping at least 50% with ground-truth bounding boxes, providing a baseline for model accuracy. Therefore, this study chooses MobileNetV3-Large as the core architecture because of its better balance between computational efficiency and detection accuracy, as shown in Fig. keywords: accuracy; detection; korla; lightweight; model; nanodet; object; orchard; pear; plus cache: fcis-31256.pdf plain text: fcis-31256.txt item: #608 of 872 id: fcis-31262 author: Du, Zeyuan; Zheng, Haoyuan; Li, Xiangyu; Zheng, Tianyu; Zhu , Sicheng title: Research on Urban Waste Sorting Transportation Path Scheduling Based on Greedy Algorithm and Clustering Optimization date: 2025 words: 3645 flesch: 64 summary: Secondly, in a multi-vehicle collaborative scenario, a multi-objective model incorporating carbon costs is constructed, solved using integer linear programming and genetic algorithms, and it is verified that transportation costs are positively correlated with the distance to collection points. The following factors are considered: The decision variable indicates whether vehicle transports waste from collection point to collection point (1 indicates yes, 0 indicates no). keywords: collection; model; point; vehicle; waste cache: fcis-31262.pdf plain text: fcis-31262.txt item: #609 of 872 id: fcis-31263 author: Bai, Junming; Hou, Bingxu; Wu, Jiansheng title: ADHD-Conformer: EEG-Based Classification and Detection of ADHD date: 2025 words: 1241 flesch: 34 summary: The proposed ADHD-Conformer is a hybrid deep neural network designed specifically for modeling the spatiotemporal characteristics of EEG signals in the context of ADHD diagnosis. This study presents an innovative deep learning approach that enhances both the accuracy and generalization of ADHD classification from EEG data. keywords: adhd; architecture; eeg; feature; model cache: fcis-31263.pdf plain text: fcis-31263.txt item: #610 of 872 id: fcis-31264 author: Li, Hao; Liu, Liyu title: Predicting Multigene Transcriptional Outcomes Based on Dual-Stream Mamba Neural Network date: 2025 words: 4540 flesch: 41 summary: The data of gene expression levels and gene perturbation were derived from the Norman, RPE1, and K562 datasets. This result indicates that the model can not only reliably predict the expression changes after gene perturbation, but also effectively capture the complex dynamic features of gene interactions, providing an analytical tool with high confidence for the precise resolution of multi-gene perturbation effects. keywords: cell; data; expression; figure; gene; mamba; mechanism; model; perturbation; prediction; stream; training cache: fcis-31264.pdf plain text: fcis-31264.txt item: #611 of 872 id: fcis-31302 author: Gong, Dafeng; Meng, Linggui; Chi, Wanle; Lin, Aichun; Shi, Lili title: Review of Real-Time Monitoring and Early Warning Technology for Natural Disasters Based on Multimodal Information Fusion date: 2025 words: 8604 flesch: 38 summary: With the rapid development of sensor technology, remote sensing technology and Internet technology, the acquisition ability of multimodal data, such as satellite images, ground sensor data, social media information, and UAV images, has been significantly improved, providing new opportunities for real-time intelligent monitoring and early warning of natural disasters. In recent years, with the popularity of multi-source data acquisition technology (such as high-resolution satellite, Internet of things equipment, UAV), researchers began to explore the fusion method of multimodal data to improve the monitoring ability. keywords: accuracy; data; disaster; flood; fusion; images; information; learning; media; model; monitoring; multimodal; remote; sensing; system; technology; time; warning cache: fcis-31302.pdf plain text: fcis-31302.txt item: #612 of 872 id: fcis-31330 author: Wei, Dongqin; Gao, Wei; Chen, Chao title: Salt Craft Visual Analytics System date: 2025 words: 3080 flesch: 34 summary: The system includes a flowchart of traditional salt production, a bubble chart of salt worker occupations, diagrams of tools and facilities related to the process, as well as visualizations of salt composition, suitable consumer groups, and geographical distribution of salt production sites. To systematically analyze the production techniques of well salt and uncover its health value, this study proposes a multidimensional visual analytics system. keywords: analysis; data; figure; making; process; salt; sea; sichuan; visualization cache: fcis-31330.pdf plain text: fcis-31330.txt item: #613 of 872 id: fcis-31331 author: Zheng, Yingjuan; Lin, Chejiacheng; Fu, Guangnu title: High-performance Single-phase AC Electronic Load Design based on Active PFC and SPWM Control Strategy date: 2025 words: 3920 flesch: 54 summary: The active PFC circuit can effectively eliminate the current waveform distortion, keep the voltage and current phase consistent, and solve the problems of power factor and electromagnetic compatibility[6]. According to different load types and set power factors, several tests were carried out, and the corresponding voltage, current and power data were recorded. keywords: circuit; control; current; design; input; load; power; voltage cache: fcis-31331.pdf plain text: fcis-31331.txt item: #614 of 872 id: fcis-31335 author: Xu, Sheng title: Algorithm Optimization and Performance Improvement of Debt Enterprise Information Retrieval System in the Big Data Environment date: 2025 words: 2512 flesch: 30 summary: Meanwhile, it is necessary to solve the contradictory signals in supervised learning, enhance the robustness and adaptability of the system in complex scenarios, and promote the evolution of debt enterprise information retrieval towards higher accuracy and real-time performance. This limitation, when mapped to debt enterprise retrieval, will seriously affect the precise correlation analysis of multi-source heterogeneous information containing unstructured data (such as scanned copies of financial reports, contract images). keywords: data; debt; enterprise; information; retrieval; risk; system; time cache: fcis-31335.pdf plain text: fcis-31335.txt item: #615 of 872 id: fcis-31410 author: Song, Jiajun title: Research on Recycling Mode of Used Power Batteries under the Perspective of Blockchain date: 2025 words: 7239 flesch: 32 summary: These companies have developed a mature 'recycling + secondary use' model for power battery recycling, focusing on the entire lifecycle value chain of new energy vehicles: 'battery recycling-raw material regeneration-material regeneration-battery pack regeneration-new energy vehicle service.' After receiving products from manufacturers, these stores are responsible for both sales and battery recycling. keywords: batteries; battery; battery recycling; chain; companies; energy; enterprises; information; model; power; power batteries; recycling; utilization; vehicles cache: fcis-31410.pdf plain text: fcis-31410.txt item: #616 of 872 id: fcis-31417 author: Zhong, Liyan title: Multimodal Model Based on CT Images and Liquid Biopsy to Predict Lung Cancer Survival date: 2025 words: 5027 flesch: 44 summary: [8] Chen, Y., Chu, X., Yu, X. & Su, C. Research progress of prediction models related to the efficacy of immune checkpoint inhibitors. It is worth noting that although the performance of the imaging omics + clinical model (C-index=0.801) and the liquid biopsy + clinical model (C-index=0.779) was better than that of the single clinical model (C-index=0.712), it was still inferior to the multimodal model, suggesting that simply superimposing clinical features cannot replace the complementary role of multimodal features. keywords: accuracy; biopsy; cancer; imaging; index; liquid; lung; model; multimodal; patients; prediction; stage; survival cache: fcis-31417.pdf plain text: fcis-31417.txt item: #617 of 872 id: fcis-31419 author: Miao, Kunlin; Wang, Runliu title: Design and Implementation of Intelligent Water Dispenser System date: 2025 words: 5044 flesch: 48 summary: It can flexibly switch between maintaining water temperature and heating water temperature according to the user's actual needs. For instance, water temperature can be adjusted, and some water dispensers even have the ability to purify water quality[4]. keywords: control; design; function; level; stm32; system; temperature; user; water; water dispenser; water temperature cache: fcis-31419.pdf plain text: fcis-31419.txt item: #618 of 872 id: fcis-31420 author: Cheng, Zixi title: Design of Face Recognition Course Checking System date: 2025 words: 3590 flesch: 42 summary: By integrating facial recognition technology into teaching management, precise analysis of students' learning behavior can be achieved. Facial recognition technology can be connected to intelligent teaching devices. keywords: accuracy; attendance; feature; mobilefacenet; model; recognition; siamese; system; technology cache: fcis-31420.pdf plain text: fcis-31420.txt item: #619 of 872 id: fcis-31421 author: Wen, Rui title: Large-scale Fire Detection based on YOLOv8 Lightweight Model and its Improved System date: 2025 words: 6346 flesch: 43 summary: Nowadays, computer vision methods and video surveillance cameras have a wide range of applications, has shifted from traditional detection methods to machine deep learning technology, these technologies have a very important role in promoting and significance of fire detection, image detection can be extracted through the dataset training after the object features, compared with the traditional fire detection methods, it can detect and warn of fires in a short period of time, and the coverage of the area is wider, and can realize a wide range of detection. The application of YOLOv8-based model in fire detection can greatly reduce the consumption of manpower and financial resources for detection, and reduce the economic losses caused by fire. keywords: accuracy; cnn; data; detection; feature; fire; fire detection; flame; learning; model; multimodal; network; performance; smoke; time; yolov8 cache: fcis-31421.pdf plain text: fcis-31421.txt item: #620 of 872 id: fcis-31433 author: Ge, Jiawei; Zhu, Jianjun title: A Self-Adaptive Heterogeneous Ant Colony Algorithm for Path Planning date: 2025 words: 3616 flesch: 38 summary: To address the issues of rigid subgoal mapping and algorithm local convergence in robot path planning within static unknown environments, Xu[6] proposes a dynamic subgoal mapping strategy and an ACO-PSO hybrid optimization framework. Introduction With the continuous advancement of automation technology, global path planning plays a vital role in fields such as autonomous vehicles, mobile robots, and industrial automation assembly lines. keywords: aco; algorithm; ant; colony; convergence; optimization; path; pheromone; planning; system cache: fcis-31433.pdf plain text: fcis-31433.txt item: #621 of 872 id: fcis-31449 author: Qian, Yu; Li, Yanping title: The Design and Implementation of Meeting Reminder System Based on uni-app date: 2025 words: 4171 flesch: 46 summary: However, the drawbacks of the traditional meeting management model are becoming increasingly prominent: firstly; as the transmission of meeting information relies on decentralized channels such as emails and instant messaging tools, it is easy to cause information omissions; according to a certain survey results, approximately 28% of people in the workplace have missed important meetings due to the failure to receive meeting notifications in time; secondly, frequent time conflicts and the difficulty in real-time synchronization and manual recording of schedules have led to 15% of meetings being rescheduled due to time conflicts among participants; thirdly, the supporting services for large-scale meetings (such as document search, seat positioning, and transportation arrangement) lack a unified access point, which requires participants to switch between multiple applications and results in a relatively poor experience. The front-end page can obtain meeting information, weather information, etc. through the calling interface to ensure the accuracy and stability of data transmission. keywords: app; data; design; information; management; meeting; module; page; system; time; uni; users; weather cache: fcis-31449.pdf plain text: fcis-31449.txt item: #622 of 872 id: fcis-31450 author: Liu, Yuanyuan; Xu, Haiqian title: Intelligent Vehicle Target Detection based on ARM Processor and Microcontroller date: 2025 words: 1962 flesch: 33 summary: Traditional intelligent vehicle object detection systems leveraging microcontrollers typically employ conventional machine learning techniques, such as edge detection and classifiers (HOG, SIFT, SVM, AdaBoost). Due to its efficiency and flexibility, MobileNet is widely used image classification, object detection, and many other computer vision tasks. keywords: convolution; detection; model; object; vehicle; yolov5 cache: fcis-31450.pdf plain text: fcis-31450.txt item: #623 of 872 id: fcis-31454 author: Zhang, Xinchen; Zhao, Xiaoyi; Wang, Shasha title: Optimization of Agricultural Product Quality and Safety Traceability Systems in a Multi-Chain Collaborative Framework date: 2025 words: 3306 flesch: 29 summary: The state synchronization stage relies on a lightweight relay chain for cross-chain data alignment, and a dedicated compression algorithm based on Huffman coding is developed to reduce the synchronization bandwidth consumption by 56%. Consumers' demands for food safety are continuously increasing, and regulatory authorities are paying more attention to the construction of agricultural product traceability systems. keywords: architecture; blockchain; chain; collaborative; data; layer; multi; product; quality; system; traceability; transaction cache: fcis-31454.pdf plain text: fcis-31454.txt item: #624 of 872 id: fcis-31478 author: Tang, Lei; Wang , Wende; Fu, Yangcan; Li, Hongming; Wang, Lin; Zhao, Bingfeng title: Research on the Smart Operations and Maintenance Platform for Fishery-photovoltaic Stations Robots Based on Reinforcement Learning date: 2025 words: 4091 flesch: 36 summary: Currently, the intelligent operation and maintenance of photovoltaic power plants is showing a trend toward robot replacement [3]. [2] Wang, H., Yan, H., Ye, H.R., Bai, S. & Li, Y.D. Intelligent inspection of photovoltaic power stations based on drones. keywords: algorithm; data; energy; group; inspection; learning; maintenance; operation; photovoltaic; platform; power; water cache: fcis-31478.pdf plain text: fcis-31478.txt item: #625 of 872 id: fcis-31522 author: Li , Jianhong; Liang, Yan; Zheng, Hui title: Optimization of BP Neural Network Image Restoration based on Improved Cuckoo Algorithm date: 2025 words: 2508 flesch: 52 summary: Abstract: To address the limitations of BP neural networks, such as their sensitivity to initial weights and thresholds and their tendency to get stuck in local optima, this paper uses the cuckoo algorithm to search for the initial weights and thresholds of BP neural networks, thereby eliminating their dependence on initial weights and thresholds. Applying BP neural networks to image restoration problems holds significant potential and promise for future development. keywords: algorithm; cuckoo; image; network; neural; restoration cache: fcis-31522.pdf plain text: fcis-31522.txt item: #626 of 872 id: fcis-31581 author: Tang, Lei; Hong, Wei; Liu, Xuanming; Xing, Xudong; Wang, Xuehao; Hu, Hejiang title: Research on the Image Recognition Framework for Drone-Based Inspection of Photovoltaic Plants Powered by Deep Learning date: 2025 words: 3840 flesch: 43 summary: [4] Li, B., Zhao, K., Bai, Y., Guo, C., Xu, W., Xu, D. & Zhai, Y. Photovoltaic panel infrared image defect detection based on YOLOv7-EPAN. Types and Characteristics of Photovoltaic Power Plant Defects Photovoltaic module defects can be categorized into two main categories: electrical defects and physical defects. keywords: accuracy; defect; detection; feature; framework; image; learning; model; module; photovoltaic; power; recognition cache: fcis-31581.pdf plain text: fcis-31581.txt item: #627 of 872 id: fcis-31585 author: Gan, Xingyu title: Research on Agricultural Film Recycling Mechanism Based on Intelligent Optimization Algorithms and Game Theory date: 2025 words: 3361 flesch: 36 summary: By running the model, the main factors influencing agricultural film recycling costs and their weights were identified, as shown in Table 1. sin(2 ) Through the Wolf Pack Optimization Algorithm model, the key factors influencing agricultural film recycling costs were systematically analyzed, and economically feasible parameters for the recycling cost coordination mechanism were optimized. keywords: agricultural; algorithm; cost; enterprises; film; game; government; model; recycling; wolf cache: fcis-31585.pdf plain text: fcis-31585.txt item: #628 of 872 id: fcis-31596 author: Wang, Tiantian; Qi , Zhenhao; Ding, Zhicheng title: A Community Detection Method based on Formal Concept Lattice date: 2025 words: 3650 flesch: 56 summary: Tiantian Wang Abstract: Community detection aims to uncover groups of vertices in a network that are more closely connected to each other than to the rest of the graph. [1], while Infomap approaches community detection from an information-theoretic perspective by minimizing the description length of random walks keywords: analysis; communities; community; concept; detection; set cache: fcis-31596.pdf plain text: fcis-31596.txt item: #629 of 872 id: fcis-31597 author: Li, Run; Liu, Fangjun title: YOLO-AlignRank: Cross-Scale Deformable Head and Rank-Consistent Loss for One-Stage Object Detection date: 2025 words: 6002 flesch: 48 summary: In other words, candidates with higher IoU (better localization, shown in green) are assigned higher classification scores than those with lower IoU (shown in red). Because candidate ordering before and after NMS is largely driven by classification scores, high-IoU predictions are often suppressed while poorly localized but high-score boxes survive. keywords: classification; cross; detection; head; iou; loss; object; quality; ranking; rcq; scale; training; yolo cache: fcis-31597.pdf plain text: fcis-31597.txt item: #630 of 872 id: fcis-31607 author: Zhang, Mingyu title: Design and Implementation of a Flexible Raindrop Sensor date: 2025 words: 4896 flesch: 26 summary: Against the backdrop of the interweaving of a new round of technological revolution and industrial transformation, comprehensively strengthening the dominant position of enterprises in technological innovation, driving the organic integration and mutual promotion of the organized mission- driven innovation ecosystem led by leading technology enterprises and the distributed emergent innovation ecosystem led by pioneering technology enterprises (with scenarios as the driver) has become a key engine for upgrading the national strategic sci-tech strength and comprehensively improving the efficiency of the national innovation system. Against the backdrop of accelerating the in-depth integration of technological innovation and industrial innovation, achieving high-level technological self-reliance and self-improvement, and building a world power in science and technology, it is of great significance to study how to replicate Hangzhou's innovative genes in Suzhou. keywords: capital; chain; development; enterprises; hangzhou; industrial; innovation; integration; market; research; support; talent; technology cache: fcis-31607.pdf plain text: fcis-31607.txt item: #631 of 872 id: fcis-31608 author: Qin, Lihao; Ma, Zhongyu; Zhang, Zhanshuo; Zuo, Yongfeng; He, Dan title: Research on a Non-Contact Cattle Weight Measurement System Based on Deep Learning date: 2025 words: 3121 flesch: 45 summary: [6] Liu W. Research on cattle body size measurement methods based on deep learning [D]. [7] Guan X P. Research on cattle body size measurement methods based on depth estimation [D]. keywords: body; cattle; detection; keypoint; learning; measurement; model; size; weight cache: fcis-31608.pdf plain text: fcis-31608.txt item: #632 of 872 id: fcis-3162 author: Zhang, Ni title: A Review of Security Research on the Internet of Things, Based on Artificial Intelligence and Blockchain date: 2022 words: 2556 flesch: 45 summary: The security features of blockchain, such as its resistance to tampering, its traceability, and its anonymity are all utilized to provide a guarantee for IoT data security and safe information transmission. The measurement chain, on the other hand, is derived from the main chain and ensures data security by running its own independent blockchain and uploading valuable information to the main chain on a regular basis. keywords: blockchain; data; intelligence; iot; layer; learning; network; security cache: fcis-3162.pdf plain text: fcis-3162.txt item: #633 of 872 id: fcis-31621 author: Tian, Ruixuan title: Research on House Price Forecasting in Guiyang City Based on ARIMA and GARCH Models date: 2025 words: 4483 flesch: 58 summary: Abstract: The purpose of this study is to forecast and analyze the house price of Guiyang city through ARIMA model and GARCH model, in order to improve the accuracy and reliability of house price prediction, and to provide references for real estate market analysis and policy formulation. This study will use the average residential transaction price data of Guiyang city from 2019 to 2024 to firstly analyze the smoothness and autocorrelation of the house price data by ARIMA model to capture the trend and seasonal changes in the time series; secondly, analyze the volatility of house price by GARCH model to capture the conditional heteroskedasticity phenomenon in the market. keywords: arima; arima model; data; garch; garch model; model; price; test cache: fcis-31621.pdf plain text: fcis-31621.txt item: #634 of 872 id: fcis-31622 author: Fu, Ziang title: Design and Implementation of a Group Tour Information System for South of the Clouds Based on the SSM Framework date: 2025 words: 2997 flesch: 38 summary: Data access methods are declared within Mapper interfaces; for example, the UserMapper may contain User selectUserById(Long userId); to retrieve user information by ID. The UserService interface defines a series of business methods related to user operations, such as User getUserById(int userId); for retrieving specific user information by user ID. keywords: data; database; design; framework; group; implementation; information; layer; system; tour; tourism; travel; user cache: fcis-31622.pdf plain text: fcis-31622.txt item: #635 of 872 id: fcis-31623 author: Guan, Xin title: Exploring the Depths of User Interest: How LLMs are Revolutionizing Personalized Shopping date: 2025 words: 3624 flesch: 30 summary: The driving force behind this transformation stems from the challenges to traditional personalized marketing methods, and the rise of large language models injects a more intelligent and flexible impetus into personalized marketing. The emergence of large language models has brought about a disruptive change to personalized marketing. keywords: commerce; data; language; llms; models; needs; product; recommendation; systems; time; users cache: fcis-31623.pdf plain text: fcis-31623.txt item: #636 of 872 id: fcis-31631 author: Wang, Xi title: A Multimodal Analysis of Human Imitation of AI and Human–Machine Relations: A Case Study of 50 TikTok Videos date: 2025 words: 4681 flesch: 38 summary: The shifts in written language modality and auditory modality (music) serve as cues for the audience to recognize the transition from normal performance to AI imitation. Existing scholarship has primarily focused on AI imitating humans within the paradigm of mimesis in intelligent media contexts, while some studies have used mimesis as an analytical lens to examine imitation behaviors in short videos, highlighting how individuals pursue a sense of belonging in virtual networks and how authentic human life becomes increasingly separated from, and alienated by, mediated representations (Sun Yuting, 2020) keywords: analysis; content; elements; human; imitation; machine; multimodal; phenomenon; relations; video cache: fcis-31631.pdf plain text: fcis-31631.txt item: #637 of 872 id: fcis-31632 author: Wang, Zenghua title: Analysis on the Method of Improving the Performance of Natural Language Processing Model Driven by Artificial Intelligence date: 2025 words: 2409 flesch: 39 summary: As shown in Figure 1, the framework covers data layer, model layer, training layer and deployment layer: in the data layer, low-resource data enhancement and knowledge injection technology are adopted to reduce the dependence on large-scale annotation data [3]; Design a dynamic sparse compression architecture in the model layer, taking into account the model accuracy and computational efficiency; Adaptive multi-task joint learning strategy is introduced in the training layer to enhance the generalization ability of the model in cross-domain and cross-task scenarios [4-5]; Multi-modal semantic alignment reasoning is realized in the deployment layer, which supports efficient and accurate interaction in complex real scenes. As shown in Table 1, on FLORES-200, the BLEU reaches 47.5, on X-Cross, the macro F1 reaches 84.7, the reasoning delay of edge devices is reduced to 62ms, and the energy consumption is reduced to 2.9J, which verifies the effectiveness and superiority of collaborative optimization among data layer (AKI), model layer (DSGT) and training layer (MAMTL). keywords: cross; data; knowledge; language; layer; model; performance cache: fcis-31632.pdf plain text: fcis-31632.txt item: #638 of 872 id: fcis-3164 author: Zhang, Ziyi; Ding, Xuewen title: Small pedestrian target detection based on YOLOv5 date: 2022 words: 1771 flesch: 54 summary: Abstract: YOLOv5s is the network with the smallest depth and feature map width and the fastest image inference, but when applied to small pedestrian target detection in complex scenes, the detection still suffers from wrong and missed detections. As pedestrian detection in realistic environments is unavoidably affected by the environment, e.g. exposure and shadow surfaces due to strong daylight exposure; blurred pedestrian features caused by foggy[5] and rainy[6] weather; the distance of pedestrians from the camera in surveillance scenes, which can lead to differences in scale spanning; and the small pedestrian problem caused by the dense pedestrian flow in special scenes such as high-speed railway stations, airports, and public gathering places[7] can all affect the effectiveness of detection. keywords: accuracy; detection; figure; model; network; pedestrian; spd; yolov5s cache: fcis-3164.pdf plain text: fcis-3164.txt item: #639 of 872 id: fcis-3166 author: Yu, Li; Zhao, Chenlei; Yang, Yong; Wu, Shenghong title: Investigation report of aero engine air die hole processing date: 2022 words: 2138 flesch: 53 summary: Among them, laser microhole machining is one of the earliest and most widely used technologies in laser technology. Compared with traditional machining methods, laser microhole machining is a more effective machining method. keywords: engine; film; gas; hole; laser; machining; processing; technology cache: fcis-3166.pdf plain text: fcis-3166.txt item: #640 of 872 id: fcis-31660 author: Zhao, Hongzhe title: Interpretable Olympic Medal Forecasting Using Hybrid GA-LSTM with SHAP Explanations date: 2025 words: 3791 flesch: 55 summary: Uncertainty in medal predictions: The GA-LSTM model helps NOCs understand the expected number of medals in different scenarios, especially in some specific events, by predicting the number of Olympic medals and providing confidence intervals, which helps the NOCs to understand the expected number of medals in different scenarios, especially in some specific events, and helps to identify potential challenges and opportunities in advance. This study focuses on the prediction of Olympic medals and the analysis of related factors. keywords: analysis; gold; impact; medals; model; number; olympic; prediction; set cache: fcis-31660.pdf plain text: fcis-31660.txt item: #641 of 872 id: fcis-31661 author: Li, Zhipeng title: Research on Apple Internal Quality Classification Based on Near-Infrared Spectroscopy date: 2025 words: 2534 flesch: 47 summary: The near-infrared spectral data of apple samples were collected using a near-infrared spectrometer (model ATP8600, wavelength range 997-1708nm, Optiancheng Company), as shown in Figure 1. The sugar content values of apple samples were collected using a handheld refractometer (ATAGO PAL- BX|ACID8, with a detection range of soluble sugar from 0.0 to 90%, an accuracy of ±0.2%, and a suitable temperature range of 9.0 to 99.9℃), as shown in Figure 2. keywords: classification; data; infrared; model; preprocessing; quality cache: fcis-31661.pdf plain text: fcis-31661.txt item: #642 of 872 id: fcis-31662 author: Fu, Haojing; Liang, Rui; Lin, Shaoze; Li, Xiao title: Study on the Generation of Tumor Individualized Treatment Schemes Based on Large Language Models and Literature Retrieval date: 2025 words: 3266 flesch: 29 summary: [6]), and model schemes feed back to the improvement of clinical data [2], finally generating treatment schemes suitable for patients and realizing in-depth collaboration and continuous optimization of clinical data, literature knowledge, and model decision-making. The research indicates that integrating large language models and literature retrieval technology can effectively improve the accuracy and evidence-based nature of tumor individualized treatment schemes, providing strong support for clinical decision-making. keywords: data; decision; evidence; generation; knowledge; literature; medical; model; schemes; treatment; tumor cache: fcis-31662.pdf plain text: fcis-31662.txt item: #643 of 872 id: fcis-31663 author: Xue, Yanan; Li, Zhipeng title: Research on Non-destructive Detection of Kiwi Fruit Internal Quality Based on Deep Learning date: 2025 words: 4450 flesch: 46 summary: To improve the accuracy and efficiency of fruit quality classification, this paper takes kiwifruit as the research object and proposes a non-destructive detection technology that integrates near-infrared spectroscopy technology and deep learning models to achieve kiwifruit quality classification based on soluble solid content (SSC). This study indicates that the combination of near-infrared spectroscopy data with deep learning algorithms, especially BiLSTM and multi-head attention mechanism, can effectively improve the performance of kiwi fruit quality classification, bringing new ideas and methods to the field of fruit quality detection, and meeting the requirements of modern fruit industry for rapid and non-destructive detection. keywords: accuracy; bilstm; classification; data; figure; fruit; model; quality; rate; table; type cache: fcis-31663.pdf plain text: fcis-31663.txt item: #644 of 872 id: fcis-3167 author: Tan, Jielong title: Development and Technology Application of Smart hospitals in China date: 2022 words: 7244 flesch: 36 summary: Smart medical care is one of the three major directions of smart hospitals construction, and its intelligent realization is inseparable from the technical support of big data and artificial intelligence technology applications. Development stages of smart hospitals in China In recent years, various Chinese hospitals have explored and built smart medical services at different levels, effectively promoting the development of China's medical informatization construction from the digital hospital stage to the smart hospitals’ construction stage. keywords: application; care; china; construction; data; development; health; hospitals; information; intelligence; internet; management; medical; technology; things cache: fcis-3167.pdf plain text: fcis-3167.txt item: #645 of 872 id: fcis-31674 author: Zhang , Jiaqi; Zhang, Dongpo; Huang, Xiaoqian title: Survey on Data-driven Intelligent Computing and Its Applications date: 2025 words: 5302 flesch: 44 summary: Intelligent computing models include supervised learning, unsupervised learning and reinforcement learning. Intelligent computing models, especially deep learning models, have a huge demand for computing resources. keywords: algorithm; computing; data; image; learning; linear; machine; model; user cache: fcis-31674.pdf plain text: fcis-31674.txt item: #646 of 872 id: fcis-31691 author: Zhao, Chenxuan; Zhang, Qianmu; Wang, Lili ; Liu, Anjun title: Study on Consumer Cognition Evaluation Model for Internet Celebrity Food Used by AHP Method date: 2025 words: 4761 flesch: 46 summary: According to the survey results, specific indices related to consumer evaluations of ICF would be identified in order to establish an indices system. Evaluation Indices System Construction Drawing on questionnaire survey and the previous studies [13-15], 14 specific indices related to consumer evaluations of ICF were selected. keywords: ahp; brand; consumer; evaluation; experience; icf; internet; marketing; results; table; weight cache: fcis-31691.pdf plain text: fcis-31691.txt item: #647 of 872 id: fcis-3171 author: Jin, Yong title: Design and Implementation of Chess and Card Recognition System Based on Deep Learning date: 2022 words: 3610 flesch: 57 summary: China Abstract: In order to improve the speed and accuracy of mahjong factory packaging detection, the neural network-based chess and card recognition system designed in this paper mainly includes image preprocessing and image recognition. Image recognition uses the Vision Transformer neural network. keywords: attention; figure; image; mahjong; paper; recognition; transformer cache: fcis-3171.pdf plain text: fcis-3171.txt item: #648 of 872 id: fcis-31721 author: Shi , Yinhua title: Research on Computer-aided 3D Modeling Simulation Optimization Model in Mechanical Design date: 2025 words: 3756 flesch: 40 summary: In contrast, the algorithm proposed in this paper effectively balances the stress distribution in various regions through optimization design, significantly reducing the stress concentration phenomenon. Research status of precision optimization design of CNC machine tools. keywords: algorithm; design; modeling; objective; optimization; simulation cache: fcis-31721.pdf plain text: fcis-31721.txt item: #649 of 872 id: fcis-31724 author: Yu, Peng; Dong, Lin; Yin, Cheng; He, Zhenghai; Wang, Jiahui; Wang , Shuang title: Intelligent Control System for Infrared Hot Air Drying Equipment Based on PLC date: 2025 words: 3424 flesch: 45 summary: Infrared hot air drying technology demonstrates exceptional performance in applications such as high-moisture fruit and vegetable crisp production, retention of active components in traditional Chinese medicinal materials, and rapid shaping of ceramic green bodies. Conversely, excessively low drying temperatures may induce enzymatic browning reactions, promoting continuous action of polyphenol oxidases. keywords: air; chamber; control; drying; energy; heating; infrared; moisture; peel; system; temperature cache: fcis-31724.pdf plain text: fcis-31724.txt item: #650 of 872 id: fcis-31726 author: He, Zhengxuan; Frentti, Francesco; He, Chao title: A Systematic Workflow for the Design and System-Level Integration of a 2.1 GHz PIFA Antenna Using AWR date: 2025 words: 2996 flesch: 46 summary: This principle provides crucial theoretical guidance for the miniaturization and frequency tuning of PIFA antennas. [5] D. Joshna and K. Chanthirasekaran, Directivity improvement of PIFA antenna at 2.7GHz by FR4 Substrate using a combination of Shorting pin and feeding pin, in 2022 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), 2022, pp. 1-5. keywords: antenna; design; ghz; level; performance; pifa; radiation; system cache: fcis-31726.pdf plain text: fcis-31726.txt item: #651 of 872 id: fcis-3173 author: Zhang, Wen; Sun, Shibao; Yang, Huanjing title: Research on aluminum defect classification algorithm based on deep learning with attention mechanism date: 2022 words: 3548 flesch: 47 summary: Convolutional neural networks (CNNs) extract features differently from manual extraction, but learn features and extract them from the data itself, with better results and greater robustness. [12] implemented wood defect recognition classification by convolutional neural network and this method does not require complex pre-processing of images and can recognize many kinds of wood defects with high correct rate and efficiency. keywords: aluminum; classification; defects; feature; inception; information; module; network; recognition cache: fcis-3173.pdf plain text: fcis-3173.txt item: #652 of 872 id: fcis-3175 author: Zhang, Zhikang title: Advances in medical knowledge graph construction techniques and applications date: 2022 words: 2773 flesch: 42 summary: Due to the special nature of medical knowledge, medical knowledge graphs still have some distance to meet medical needs. In this paper, we explore the overall situation of medical knowledge graphs through literature retrieval and visualization analysis of medical- related knowledge graphs. keywords: alignment; entity; extraction; graph; information; knowledge; learning; medical; relationship cache: fcis-3175.pdf plain text: fcis-3175.txt item: #653 of 872 id: fcis-3177 author: Wu, Pengjin title: A Survey of Few-Shot Learning Research Based on Deep Neural Network date: 2022 words: 4985 flesch: 60 summary: Few-shot learning based on deep learning models is also a hot research topic in recent years. [15] et al. further couples the generative and classification networks together end-to-end to train a neural network adapted to few samples neural networks for learning with few-shot. 3.2. keywords: classification; dataset; learning; metric; model; network; samples; shot; shot learning; training cache: fcis-3177.pdf plain text: fcis-3177.txt item: #654 of 872 id: fcis-3178 author: Huang, Hongbin title: A facial expression recognition method based on Convolutional Neural Network date: 2022 words: 2573 flesch: 52 summary: Therefore, we decided to take turns using three datasets for training and comparison through several trials, and tried to analyse the impact of different datasets on model training. Geometric normalization is to determine the main rectangular feature region according to the sum of feature points and geometric model of facial expression image, and then cut the original size of 256×256 image into 150×100 image, so that the size of the face in the image is consistent. keywords: cnn; data; datasets; expression; fer; model; recognition; training cache: fcis-3178.pdf plain text: fcis-3178.txt item: #655 of 872 id: fcis-31786 author: Dong, Zimo title: Chord-Color Mapping for Audio-Visual Generation: Integrating Deep Learning and Emotion Quantification date: 2025 words: 3439 flesch: 39 summary: Conclusion and Discussion This study developed the Harmony and Color device, demonstrating the application of chord–color mapping in cross-sensory art. The model establishes a color-emotion-chord pathway by leveraging image color features and a chord dataset with emotional labels, trained using an LSTM architecture for emotion-driven audio- visual generation. keywords: art; chord; color; emotion; generation; image; learning; mapping; model; music; training cache: fcis-31786.pdf plain text: fcis-31786.txt item: #656 of 872 id: fcis-3179 author: Fang, Cheng title: Applications of AI in game plug-ins detection date: 2022 words: 2502 flesch: 61 summary: This is also one of the pain points of game developers. Therefore, the most popular method at present is also the method used by game developers: user behavior analysis and detection, mainly in the following 122 points: 1)Analyze the mouse click frequency and movement frequency. keywords: data; detection; game; ins; plug cache: fcis-3179.pdf plain text: fcis-3179.txt item: #657 of 872 id: fcis-3181 author: Chen, Yuye title: Intelligent information retrieval based on Ontology date: 2022 words: 1990 flesch: 43 summary: In order to perform semantic information retrieval using an ontology matching method, researchers propose a new algorithm for preprocessing and LDA-based document classification. Intelligent ontology based semantic information retrieval using feature selection and classification. keywords: information; ontology; retrieval; semantic; web cache: fcis-3181.pdf plain text: fcis-3181.txt item: #658 of 872 id: fcis-3182 author: Hou, Yaohui title: Detection of Domestic Waste Based on YOLO date: 2022 words: 1501 flesch: 58 summary: Yolov4: Optimal speed and accuracy of object detection. Rich feature hierarchies for accurate object detection and semantic segmentation. keywords: detection; model; object; waste; yolo cache: fcis-3182.pdf plain text: fcis-3182.txt item: #659 of 872 id: fcis-3183 author: Luo, Dan title: Design and implementation of automatic packing machine system based on PLC date: 2022 words: 1744 flesch: 48 summary: Automatic packaging machine control system is realized by controlling PLC and processing the peripheral circuit, the external circuit will be the system of signal transmission to the PLC control system, and then through the processing of output control requirements. Automatic packaging machine system call automatic and manual subroutine ladder diagram, as shown in Figure 4. keywords: control; machine; packaging; plc; system cache: fcis-3183.pdf plain text: fcis-3183.txt item: #660 of 872 id: fcis-31880 author: Lin, Dongjie title: Predicting Internal Control Deficiencies with Deep Learning: Evidence from IPO Review Records date: 2025 words: 6377 flesch: 40 summary: The effect of internal control weakness on investment efficiency[J]. Identification of internal control deficiencies (ICDs) based on annual report disclosures or audit opinions suffers from reporting lags and sparse positives. keywords: assets; auc; baseline; cash; control; disclosure; financial; firms; icd; information; internal; ipo; model; proxy; risk; total cache: fcis-31880.pdf plain text: fcis-31880.txt item: #661 of 872 id: fcis-31893 author: Zhu, Tianxiang title: Research on Urban Sound Classification based on ConvNeXt-FECA Model date: 2025 words: 3829 flesch: 33 summary: Meanwhile, the choice of feature extraction method has a critical impact on model performance; among the single-feature methods, Spectrogram performs the best, while the combination of fused features, especially Spectrogram and MFCC, further enhances the model's classification ability. Performance metrics of the ConvNeXt-FECA model with different feature extraction methods. keywords: accuracy; audio; classification; convnext; extraction; feature; frequency; mfcc; model; spectrogram; training cache: fcis-31893.pdf plain text: fcis-31893.txt item: #662 of 872 id: fcis-31901 author: Yang, Yichen; Du, Jiayuan title: A Hybrid Computational Framework for Regional Classification in Gravity-Aided Navigation: Integrating Hierarchical Clustering and Random Forests date: 2025 words: 1617 flesch: 30 summary: Distribution of gravity anomaly data across the study region 2.2. Distribution of gravity anomaly data in dataset 2 49 Table 1. keywords: anomaly; classification; clustering; dataset; gravity; hierarchical cache: fcis-31901.pdf plain text: fcis-31901.txt item: #663 of 872 id: fcis-31913 author: Zhang , Yuan; Ding, Xuewen; Jiang, Xiaokai; Wang, Shaosai title: Research on Wood Defect Detection Algorithms Based on Improved Neural date: 2025 words: 5309 flesch: 35 summary: Despite significant advancements in deep learning technologies for wood defect detection, existing algorithms still face limitations due to factors such as complex texture backgrounds, diversity in defect types, and some defects being small in size. Therefore, this study addresses key issues in wood defect detection by proposing a more targeted deep learning object detection algorithm aimed at improving adaptability and reliability in complex scenarios while providing more effective technical support for quality control in the wood industry. keywords: accuracy; algorithm; defect; detection; efficiency; feature; fusion; model; module; network; performance; precision; surface; wood; yolov11 cache: fcis-31913.pdf plain text: fcis-31913.txt item: #664 of 872 id: fcis-31918 author: Shi, Luetian title: Research on the Enhanced Application of Artificial Neural Network Models in Photonic Crystal Design date: 2025 words: 4690 flesch: 42 summary: To ensure that the neural network accurately learns the mapping relationship between photonic crystal parameters and band structures, the training samples are initially restricted to typical defect-free structures. ShiLveTiannjupt@outlook.com Abstract: Photonic crystals, owing to their ability to precisely control photonic dispersion and localized fields, are extensively utilized in lasers, sensing, and optical information processing. keywords: air; crystal; defect; design; hole; lattice; layer; mode; network; neural; photonic; set; training cache: fcis-31918.pdf plain text: fcis-31918.txt item: #665 of 872 id: fcis-31919 author: Song, Sirui title: Deep Learning-Driven Text Sentiment Analysis: Research Progress, Challenges, and Future Trends in the Past Five Years date: 2025 words: 2745 flesch: 40 summary: Since 2020, with intensive exploration conducted by academia, the EAAF has quantified the reliability of domain knowledge, cutting the cross-domain performance gap between medical and e-commerce areas down from 10% to 4.2%, whereas the accuracy of irony recognition with structured sentiment analysis model exceeds 75% [5,6]. Abstract: Text sentiment analysis has developed from a single text classification task into a complex multimodal fusion system that can achieve cross-scenario sentiment understanding with the help of deep learning technology. keywords: accuracy; analysis; cross; domain; learning; models; performance; sentiment; text cache: fcis-31919.pdf plain text: fcis-31919.txt item: #666 of 872 id: fcis-31924 author: Ding, Li; Yu, Minjia; Du, Zeyuan title: An Energy-Efficient Multi-Objective Optimization Framework for QoS-Aware Resource Allocation in 5G Slicing Networks date: 2025 words: 2914 flesch: 60 summary: Objective Function Based on the modeling and constraints, this study defines the objective as maximizing the cumulative QoS utility over all users and time slots:  , 10 , 1 1 max u t N u u tR t u J w Q     (28) where uW represents the priority weight of user u , which is assigned based on user class preferences. For URLLC users, the end-to-end latency id must not exceed the strict delay threshold. keywords: optimization; qos; resource; u t; u u; user cache: fcis-31924.pdf plain text: fcis-31924.txt item: #667 of 872 id: fcis-31925 author: Jiang, Siju; Guo, Ying title: Design of Hydrological Information Monitoring System Based on Single-Chip Microcomputer date: 2025 words: 1732 flesch: 42 summary: Design of a Hydrological Information Monitoring System Based on a Microcontroller [J]. Hydrological Information Monitoring System Indicator Light Circuit 3.7. keywords: design; figure; information; monitoring; system; water cache: fcis-31925.pdf plain text: fcis-31925.txt item: #668 of 872 id: fcis-31926 author: Ren, Yan; Huang, Fuchun; Jiang, Wenjie; Luo, Ruier title: Design and Performance Optimization of an Intelligent Cockpit System Based on OpenHarmony date: 2025 words: 3053 flesch: 43 summary: To realize the quantitative evaluation of system performance, communication latency models, data acquisition accuracy models, and interactive response efficiency models are established, and the effectiveness of each model is verified through experiments. It can be seen from Table 4 that this system has significant improvements in communication latency and data loss rate indicators compared with traditional systems, and also has a certain advantage in voice accuracy. keywords: accuracy; communication; control; data; formula; latency; layer; model; system; voice; 𝑇 𝑇 cache: fcis-31926.pdf plain text: fcis-31926.txt item: #669 of 872 id: fcis-31944 author: Du, Xinyang title: Research on the Effect of Data Analysis-Based Integrated Activities for People with and without Disabilities on Enhancing Inclusive Literacy Among Adolescents date: 2025 words: 3878 flesch: 38 summary: By designing and carrying out diversified integrated activities and using scientific data analysis methods to evaluate the effect of activities, the purpose is to clearly reveal the influence of such activities on adolescents' cognition, attitude and behavior. sally_duuuy@qq.com Abstract: This study focuses on the enhancing effect of integrated activities for people with and without disabilities (hereinafter referred to as integrated activities) on inclusive literacy among adolescents. keywords: activities; activity; adolescents; control; group; literacy; model; months cache: fcis-31944.pdf plain text: fcis-31944.txt item: #670 of 872 id: fcis-31973 author: Wang, Zicheng; Yang, Guochen title: Review on Construction and Application of Domain Knowledge Graphs: Cross-Domain Practices and Cutting-Edge Explorations Driven by Large Language Models date: 2025 words: 4134 flesch: 33 summary: Large language model powered knowledge graph construction for mental health exploration Education and Culture Field KG research in the education field breaks through the traditional static knowledge representation model, focusing on the dynamic process of knowledge construction and in- depth integration with educational scenarios. keywords: construction; data; entity; extraction; field; graph; knowledge; llms; method; model; multimodal; research cache: fcis-31973.pdf plain text: fcis-31973.txt item: #671 of 872 id: fcis-32028 author: Chen, Guoxing title: Research on Airport Clearance Risk Assessment Based on Combination Weighting Method - Cloud Model date: 2025 words: 4712 flesch: 47 summary: In this study, the introduction of the entropy weight method can serve as a beneficial supplement to the AHP method, reducing the subjective image of AHP, improving the rationality of weight allocation and data-driven capabilities, and providing a more accurate weight basis for airport clearance safety risk assessment. Airport clearance safety risk assessment index system First-level indicators Secondary indicators Level 3 indicators Laws, regulations and management guarantees Airport Obstacle Limitation Chart D 1 Does the obstacle restriction map conform to the actual plan? keywords: airport; assessment; clearance; cloud; evaluation; indicator; model; obstacle; risk; safety; system cache: fcis-32028.pdf plain text: fcis-32028.txt item: #672 of 872 id: fcis-32029 author: Zhou, Yichen; Xiang, Yang; Jian, Can; Jiang, Jiawei ; Zhang, Mingchang; Li, Kunpeng; Zhao, Tianhao; Jin, Yanze title: Design and Implementation of an Intelligent Control System for 3D Printers Based on Unity3D date: 2025 words: 2010 flesch: 39 summary: Suitable for digital control systems (e.g., single-chip microcomputers or PLC control) to avoid excessive control output caused by calculation overflow. PID control calculates the deviation between the desired value and actual value, and dynamically adjusts outputs using proportional, integral, and derivative operations to achieve rapid and stable system responses. keywords: control; design; pid; printer; printing; system; time; twin cache: fcis-32029.pdf plain text: fcis-32029.txt item: #673 of 872 id: fcis-32031 author: Ning, Yang; Dong, Shuai; Yu, Xiaoqian; Zhang, Shiqi title: Research on Comprehensive Performance Testing and Evaluation Method of Vehicle Parking Radar date: 2025 words: 4544 flesch: 41 summary: Specifically, it employs multiple test vehicles to conduct acoustic index tests on different types of obstacles at various testing angles. The data can be used for subsequent analysis and comparison of vehicle performance. keywords: analysis; data; frequency; parking; performance; response; signal; test; time; vehicle cache: fcis-32031.pdf plain text: fcis-32031.txt item: #674 of 872 id: fcis-32123 author: Cheng, Chuqiao title: Application of Reinforcement Learning to UAV Decision Making and Path Planning date: 2025 words: 2732 flesch: 32 summary: Research on cooperative search algorithm for UAV swarm based on multi-agent reinforcement learning. Wang S. Distributed multi-UAV cooperative search and tracking based on deep reinforcement learning. keywords: decision; environments; learning; multi; path; planning; reinforcement; uav cache: fcis-32123.pdf plain text: fcis-32123.txt item: #675 of 872 id: fcis-32124 author: Wang, Ying; Lu, Yonglai title: Research on Key Technological Breakthroughs of Natural Language Processing Technology in Intelligent Review of Intellectual Property Texts date: 2025 words: 6033 flesch: 28 summary: There is a natural semantic gap between technical texts and legal texts. Although the existing research has made phased progress, there are still obvious shortcomings: the structuring degree of technical feature extraction is insufficient, making it difficult to cope with the complex sentence structures of patent texts; 35 The integration of legal and technical knowledge is not deep, and the model's understanding of legal concepts such as novelty and creativity is superficial. keywords: core; examination; extraction; features; intellectual; knowledge; model; nlp; patent; property; review; semantic; system; technology; text cache: fcis-32124.pdf plain text: fcis-32124.txt item: #676 of 872 id: fcis-32134 author: Cui, Zewen title: Research on a SAC-Based Algorithm for UAV Autonomous Navigation and Obstacle Avoidance date: 2025 words: 4561 flesch: 49 summary: This architecture enables UAVs to realize safe navigation in dynamic obstacle environments while obeying the laws of physics. For UAV autonomous obstacle avoidance technology, researchers have proposed a variety of algorithms, which can be roughly categorized into traditional path planning algorithms and reinforcement learning algorithms. keywords: algorithm; environment; learning; obstacle; rate; reward; strategy; uav; 𝑅 𝑅 cache: fcis-32134.pdf plain text: fcis-32134.txt item: #677 of 872 id: fcis-32157 author: Yang, Tianyu; Chai, Sining title: Application of Social Media Medical Data in Public Opinion Monitoring and Psychological Counseling During Public Health Emergencies date: 2025 words: 4042 flesch: 39 summary: Social media medical data has the advantages of real-time performance, extensiveness, and diversity. Technical Processing System of Social Media Medical Data The technical processing of social media medical data is the foundation for subsequent applications. keywords: analysis; counseling; data; emergencies; feature; health; media; model; monitoring; opinion; public; text; time cache: fcis-32157.pdf plain text: fcis-32157.txt item: #678 of 872 id: fcis-32158 author: Liu, Guangxu; Nasheng, Batu; Zheng, Wei ; Lv, Liangliang; Zhang, Tianhua ; Sun, Guodong title: Small Target Defect Detection Method on Aluminum Ingot Surface based on Improved YOLOv8n-SimAM date: 2025 words: 3360 flesch: 41 summary: The innovations include: 1) constructing a high-definition aluminum ingot defect dataset based on an actual production line and systematically analyzing the scale distribution characteristics of the defects; 2) integrating the three- dimensional attention mechanism in the network backbone layer to enhance the feature extraction capability of small targets and solve the morphological diversity problem of burrs and slag inclusions; 3) through comparative experimental verification, the improved YOLOv8n-SimAM model achieved a mAP of 64.5% in aluminum ingot surface defect detection, an increase of 9 percentage points over the baseline model, and improved the detection of burrs and slag inclusions by 6.3% and 9.9% in the F1 score, respectively. SimAM model achieved a mAP of 64.5% in aluminum ingot surface defect detection, which was 9 percentage points higher than the baseline model. keywords: aluminum; attention; defect; detection; ingot; mechanism; model; performance; simam; slag; surface; yolov8n cache: fcis-32158.pdf plain text: fcis-32158.txt item: #679 of 872 id: fcis-32169 author: Sun, Mingyang; Ma, Shukui; Zhuo, Guangping; Ma, Fei; Zhang, Guanghua title: Multimodal Depression Recognition Based on Sentence-level Dynamic Multimodal Split Attention Fusion date: 2025 words: 3514 flesch: 39 summary: This module further segments sentence sequences into contiguous segments and adaptively emphasizes key modal features while suppressing redundant and noisy information through dynamic weight allocation. Sentence-Level Dynamic Multimodal Split Attention Fusion Module Existing methods often fuse sentence sequences as a whole, struggling to capture fragment dynamics and modality differences. keywords: attention; depression; feature; fusion; level; modality; model; modeling; multimodal; sentence; text cache: fcis-32169.pdf plain text: fcis-32169.txt item: #680 of 872 id: fcis-32170 author: Hu, Lei; Hu, Rui; Jin, Houtao title: Lightweight Design of Automotive Driveshaft Flange Fork Under High Torque Conditions Using ANSYS date: 2025 words: 1777 flesch: 46 summary: This study employs ANSYS Workbench software to conduct finite element analysis and structural optimization of automotive drive shaft flange forks, evaluating stress and strain under high torque conditions of 24,000 N·m. Future research directions include exploring multi-objective optimization (e.g., shape and topology co-optimization) and investigating composite material applications to further enhance weight reduction potential, thereby advancing lightweight structural design for automotive drive shaft flange forks under high-torque conditions. keywords: analysis; drive; flange; fork; optimization; shaft cache: fcis-32170.pdf plain text: fcis-32170.txt item: #681 of 872 id: fcis-32171 author: Wang, Jiaying; Wu, Bingyuan; Chen, Yinxing title: Adaptive Clustering-based Multi-modal Multi-Objective Location Optimization Algorithm date: 2025 words: 2325 flesch: 39 summary: To address the location optimization challenge, this paper constructs a mathematical model for multi-modal multi-objective location optimization as follows: Let the candidate site set be 𝐶 A self-organized speciation based multi-objective particle swarm optimizer for multi-modal multi-objective problems. keywords: algorithm; clustering; location; objective; optimization; search; solutions cache: fcis-32171.pdf plain text: fcis-32171.txt item: #682 of 872 id: fcis-32177 author: Zhou, Tianjun; Hou, Zhesheng title: Path Planning for Agricultural Robots Based on the Improved Dung Beetle Optimization Algorithm date: 2025 words: 2375 flesch: 47 summary: Different types of dung beetle populations were allocated according to the previous proportion, among which the number of rolling dung beetles was 10, the number of breeding dung beetles was 10, the number of foraging dung beetles was 13, and the number of stealing dung beetles was 17. proposed that when optimizing the dung beetle algorithm, the proportion of rolling ball dung beetles is 20%, egg ball dung beetles is 20%, foraging dung beetles are 25%, and stealing dung beetles are 35%. keywords: algorithm; beetle; dung; optimization; path cache: fcis-32177.pdf plain text: fcis-32177.txt item: #683 of 872 id: fcis-32179 author: Zhang, Qingfu; Wang, Yunsen; Zheng, Jianming; Li, Zhao; Li, Hao title: Trajectory Tracking of Open-pit Mining Trucks based on MPC and Pure Pursuit Control date: 2025 words: 3955 flesch: 58 summary: A c p t t t t t t t t N c t t t t c Np t t t t t t t t u t t u t t Y t In terms of control methodologies, path tracking algorithms can be categorized into three types: The first category includes the Pure Pursuit (PP) algorithm and the Stanley algorithm, which are based on geometric models for path tracking control. keywords: control; k t; mpc; path; t t; tracking; u t; vehicle;  ;   cache: fcis-32179.pdf plain text: fcis-32179.txt item: #684 of 872 id: fcis-32180 author: Long, Wei; Lu, Shiyue; Zhou, Xu title: Pet Snacks Drying Design based on PLC date: 2025 words: 2048 flesch: 43 summary: Schematic diagram of working principle of PLC control system Specifically, the ' fruit and vegetable identification and screening camera ' sorts large and melon fruits and vegetables, and the ' fruit and vegetable identification and screening camera 2 ' focuses on rhizomes and leafy vegetables. The temperature controller and PLC realize data transmission through the RS485 communication protocol and realize accurate temperature control, as shown in the figure. keywords: control; drying; fruits; system; temperature; vegetables cache: fcis-32180.pdf plain text: fcis-32180.txt item: #685 of 872 id: fcis-32181 author: Zhang, Jiazeng title: Exploration of Optical Vortex Preparation, Detection and Application based on Orbital Angular Momentum Characteristics date: 2025 words: 6278 flesch: 29 summary: With the development of technology, people's understanding of optical vortex fields continues to deepen, and their application research has also attracted wider attention. Canada Abstract: Optical vortices, as the core research object of singularity optics, are characterized by their spiral wavefront structure and determined photon orbital angular momentum. keywords: angular; beam; charge; field; interference; light; method; momentum; optical; phase; research; technology; vortex; vortices cache: fcis-32181.pdf plain text: fcis-32181.txt item: #686 of 872 id: fcis-32182 author: Zhang, Long; Hou, Zhesheng title: Design and Testing of a Soil Inversion and Mulching Machine date: 2025 words: 3155 flesch: 47 summary: Soil turning quality: Measure the depth of rotary tillage at 30 points (qualified for 10-20cm), screen the broken soil rate of 1m ² tillage layer (proportion of particle size ≤10mm); Film quality: Measure the flatness, damage rate, longitudinal tensile rate, and centerline deviation of the 30m daylighting surface; Quality of covering soil: Measure the width (8-12cm qualified), thickness (2-3cm qualified), and degree of soil leakage at the edge of the membrane; Homework efficiency: Measure 3 sets of 0.2hm ² homework time and calculate the average productivity. A large amount of water is lost due to evaporation and leakage, and long-term use can damage the soil structure, leading to soil compaction, decreased air permeability, and affecting the development of vegetable roots[3]. keywords: covering; film; machine; mechanism; power; rotary; soil; tillage; turning cache: fcis-32182.pdf plain text: fcis-32182.txt item: #687 of 872 id: fcis-32183 author: Zi, Yonghui; Miao, Yingying; Pi, Cairong title: The Transformation of Computer Fundamentals Education Driven by “DeepSeek”: -- Taking the Course “Principles of Computer Composition” as an Example date: 2025 words: 2899 flesch: 30 summary: Students Proficient in utilizing modern computer hardware and software environments and tools, gain insight into cutting-edge developments within the computer science discipline, and develop into versatile professionals equipped with solid theoretical foundations, broad specialized knowledge, strong character, innovative thinking, and robust capabilities in computer application system analysis, design, and engineering practice [2]. Through the study of Computer Organization Principles, students will develop a systematic perspective on computer architecture. keywords: computer; education; knowledge; learning; memory; principles; students; teaching cache: fcis-32183.pdf plain text: fcis-32183.txt item: #688 of 872 id: fcis-32198 author: Xing, Yu title: Learner Motivation and Engagement in Generative AI-Assisted Second Language Acquisition: A Narrative Review date: 2025 words: 5459 flesch: 37 summary: It investigates how AI tools influence these dimensions across various educational contexts, particularly in comprehensive skills. Fourthly, the technical aspects are scrutinized, identifying the type of AI tool utilized, such as ChatGPT, Claude, LLM API, or automatic scoring systems, and the nature of the AI intervention, whether it served as an assistant, a substitute, or a co-creator in the learning process. keywords: chatgpt; engagement; language; learners; learning; motivation; students; studies; tools cache: fcis-32198.pdf plain text: fcis-32198.txt item: #689 of 872 id: fcis-32208 author: Tian, Tian; Chen, Tianqi title: Causal Entropy–Driven Generative Adversarial Learning for Anomalous Event Detection in Social Networks date: 2025 words: 8090 flesch: 51 summary: [28]: A statistical method for log event detection based on mention anomaly analysis, MABED relies solely on tweets and utilizes the frequency of dynamically inserted links (mentions) in tweets to detect significant events and estimate their impact on the population. [16] utilized probabilistic models to identify log events by uncovering latent topic distributions, whereas Xie et al. keywords: anomaly; causal; data; detection; discriminator; entropy; events; generator; information; log; lstm; model; network; t t; vol cache: fcis-32208.pdf plain text: fcis-32208.txt item: #690 of 872 id: fcis-32254 author: Zhou, Ran; Li, Jianlei title: Application of Sparse Kernel Graph-regularized Discriminant Non-negative Matrix Factorization in Image Clustering date: 2025 words: 2864 flesch: 56 summary: For an element ijv in matrix V (from the objective function), the formulas for the first-order partial derivative ' ijv M and the second-order partial derivative ' ijv M of the objective function with respect to ijv can be obtained as follows: ' ( 2 2 2 2 2 ) ij T v XU UU T l ij M K VK Q A V A A LV            (12) ' 2( ) 2 ( ) 2 , 2( ) 2 ,ij T UU jj jj ii The model of the algorithm is presented as follows: 2 2 l 0, 0 2 0 1 min ( ) ( ) Tr( ) T T F FU V T F X U V Q AV V LV U U V                (1) Similar to the standard NMF model, the optimization problem of solving U and V simultaneously is non-convex. keywords: t t cache: fcis-32254.pdf plain text: fcis-32254.txt item: #691 of 872 id: fcis-32412 author: Pak , Jay title: Neuro-Morphic Hardware for Real-Time Embodied Cognition in Humanoid Robots date: 2025 words: 2463 flesch: 31 summary: This work outlines an integrated research study of neuromorphic hardware and spiking neural network architecture for providing real-time embodied cognition over a humanoid robotic platform. These outcomes indicate a direction for a potential use of neuromorphic hardware, when co-designed alongside embodied control algorithms, as providing a direction for energy-efficient, low-latency cognitive behavior in humanoid robots. keywords: adaptation; control; event; hardware; humanoid; latency; line; time cache: fcis-32412.pdf plain text: fcis-32412.txt item: #692 of 872 id: fcis-32462 author: Chen, Shuang; Diao, Nannan title: Code Commit Health (CCH): An Effective and Accessible Metric for Quantifying Development Code Contributions date: 2025 words: 5158 flesch: 49 summary: Introduction At present, the majority of companies and organisations continue to employ two single metrics, namely lines of code (LOC) or the number of code commits (NOC), to assess the contributions of programmers. This is primarily attributable to the fact that, despite ranking 6th in terms of the number of commits, his average number of lines of code commits is only slightly below the overall average of 578. keywords: cch; code; commits; contribution; data; lines; loc; metrics; noc; number cache: fcis-32462.pdf plain text: fcis-32462.txt item: #693 of 872 id: fcis-32489 author: Song, Pengfei; Lu, Haoyue title: Document-level Relation Extraction based on Graph Convolutional Neural Networks date: 2025 words: 4403 flesch: 47 summary: Conclusion This paper proposes a document-level relation extraction method based on graph convolutional neural networks, which learns the context information of entities through word embeddings, aggregates entity feature information using graph convolutional neural networks, and extracts long- distance dependency features using deep graph convolutional networks. China Abstract: The objective of extracting relations between document components lies in identifying the Within a single document, the focus often lies on understanding the connections between different entities. keywords: dataset; document; entities; entity; extraction; graph; information; methods; model; networks; neural; relation; sentence cache: fcis-32489.pdf plain text: fcis-32489.txt item: #694 of 872 id: fcis-32490 author: Chen, Ming title: High-Resolution Inversion of Seismic Stress Fields and Dynamic Hazard Analysis via Adaptive Physics-Informed Neural Networks and NGL GNSS Data Fusion date: 2025 words: 2806 flesch: 47 summary: Surface deformation being a straight reaction to stress concentration and adaptation in the crust, GNSS velocity fields make a useful source of data in the inversion of stress fields. We suggest a GNSS- based inversion of seismic stress field by an Adaptive-PINN. keywords: adaptive; data; field; gnss; hazard; inversion; physical; physics; stress cache: fcis-32490.pdf plain text: fcis-32490.txt item: #695 of 872 id: fcis-32529 author: Luo, Jinhui; Luo, Li; Yu, Xiangyang; Guo, Yuchen; Hong, Weibin title: Rapid and Non-destructive Detection of Sucrose Content in Tea by Near-Infrared Spectroscopy date: 2025 words: 4042 flesch: 51 summary: Schematic diagram of the experimental setup for spectral acquisition from tea samples. Near-infrared (NIR) reflection spectra of green tea samples (a) (b) (c) (d) Figure 3. keywords: analysis; calibration; content; infrared; method; model; near; spectroscopy; sucrose; tea; wavelength cache: fcis-32529.pdf plain text: fcis-32529.txt item: #696 of 872 id: fcis-32667 author: Liu, Yaji; Zhao, Jiamin; Xu, Xiaoqian title: Research on the Auxiliary Learning Mechanism of BIM (Building Information Modeling) Course in the Curriculum System of Architectural Engineering Technology Major date: 2025 words: 2826 flesch: 22 summary: Visualization of Model Outcomes: Visually Present the Growth Trajectory of Capabilities Unlike traditional course designs that only require the submission of two-dimensional drawings, BIM courses require students to submit a complete digital outcome that includes three-dimensional models + bill of quantities + construction progress simulation + operation and maintenance information. In traditional construction technology courses, students can only understand engineering accidents such as collapse of high formwork support systems and pipeline collisions leading to rework through case analysis, lacking intuitive cognition [4]. keywords: bim; building; construction; course; engineering; model; students; technology cache: fcis-32667.pdf plain text: fcis-32667.txt item: #697 of 872 id: fcis-32671 author: Zeng, Yisheng title: Research on Task Assignment and Path Planning Algorithm for Multi-UAV Collaboration date: 2025 words: 3560 flesch: 23 summary: Three Classic Integration Approaches: Sequential, Iterative, and Joint Integrated approaches for multi-UAV task assignment and path planning are central to resolving their strong coupling, hinging on accurately estimating and feeding back task execution costs (primarily determined by path length/time). Mixed integer programming for multi-vehicle path planning. keywords: algorithms; allocation; communication; optimization; path; planning; scale; task; uav cache: fcis-32671.pdf plain text: fcis-32671.txt item: #698 of 872 id: fcis-3300 author: Wei, Sihao title: Asset allocation strategy based on CRITIC method and BP neural network date: 2022 words: 3948 flesch: 49 summary: Using 100 securities in the China Securities Dividend Index as index samples, firstly, a BP neural network prediction model is established for prediction, then the CRITIC method is used to evaluate and score the 100 securities, and finally a multi-objective planning model is established for investment portfolio. The reliability, versatility and reliability provide references for investors to make investment portfolios. keywords: investment; method; model; portfolio; securities cache: fcis-3300.pdf plain text: fcis-3300.txt item: #699 of 872 id: fcis-3302 author: Sun, Jie; Qiu, Degui; Xu, Zhufa title: Design of Automatic Management System of Electric Power Marketing Charges and Accounts Based on Robot Process Automation date: 2022 words: 3603 flesch: 44 summary: Conclusions As the core business of electric power system, electric power marketing has been improved and sublimated on the basis of the four-tier structure proposed by the former State Electric Power Company, with more business information interaction and closer cross-departmental business process collaboration, thus forming a network electric power marketing application. As the core business of the electric power system, electric power marketing has improved and sublimated its business structure on the basis of the four- tiered structure proposed by the original State Electric Power Corporation. keywords: automation; data; electric; management; marketing; meter; power; process; rpa; system; time cache: fcis-3302.pdf plain text: fcis-3302.txt item: #700 of 872 id: fcis-3343 author: Ma, Qingzhuang; Yin, Yongqi; Shi, Xueqian title: Review of Research Methods for Hypersonic Vehicle Reentry Trajectory Planning date: 2022 words: 3277 flesch: 36 summary: This paper introduces the current research status of traditional trajectory planning methods and reinforcement learning methods, and proposes that the reentry trajectory planning methods will be intelligent in the future. Trajectory planning method based on optimization/intelligent algorithm Trajectory planning often needs to make the aircraft meet process constraints and terminal constraints to plan a trajectory with the best index, that is, trajectory optimization problem. keywords: algorithm; control; guidance; learning; method; optimization; planning; reentry; reinforcement; trajectory cache: fcis-3343.pdf plain text: fcis-3343.txt item: #701 of 872 id: fcis-3345 author: Ni, Jiayu; Huang, Baoxiang title: Research on the Fast Construction Method of Basic Geographic Framework of 3D Smart Community date: 2022 words: 3017 flesch: 44 summary: [4] By calling geometric data processing functions provided by CityEngine, two- dimensional surveying and mapping data are used to realize the programmed building of building models. Keywords: Smart community; Hierarchical household model; Dynamic rendering single; STANet; Address matching; Cesium. keywords: address; building; community; data; household; level; matching; model; photography cache: fcis-3345.pdf plain text: fcis-3345.txt item: #702 of 872 id: fcis-3732 author: Tang, Yuxin; Li, Chenjie; Chen, Shidong; Yuan, Xiufang title: The Application of IOT Technology in The Production Management of Baijiu date: 2022 words: 4137 flesch: 38 summary: (2) The data collection layer is an important carrier for database construction to realize multi-dimensional real-time data display, and the database content mainly comes from the data in the process of production and business management, and the collected contents are: production raw material information, geographic and environmental information, production and processing information, logistics and transportation information, terminal sales information, etc. (3) The application service layer is a variety of application systems for liquor production management, mainly including intelligent production monitoring systems for liquor, liquor traceability query systems, and employee on-duty management systems. This paper introduces the present situation of the research and application of the development of the Internet of things in liquor production management in the new period， and establishes a monitoring and traceability system for the whole process of liquor production around intelligent management and automatic production. keywords: application; data; development; industrial; information; internet; iot; liquor; management; monitoring; production; system; technology; things cache: fcis-3732.pdf plain text: fcis-3732.txt item: #703 of 872 id: fcis-3734 author: Cai, Lijie; Wang, Xiaoyin title: Construction of a model for calculating average tortuosity of porous media based on optimal fractal structure date: 2022 words: 4324 flesch: 50 summary: Keywords: Average tortuosity; Sierpinski carpet; Porous media materials; Heat flow paths. Calculation of average tortuosity based on heat flow paths The tortuosity i is defined as: ei i i L L  = (1) where eiL is the true length of the curved pore channel; iL is the linear length at both ends of the curved pore channel. keywords: carpet; fractal; media; model; tortuosity; unit cache: fcis-3734.pdf plain text: fcis-3734.txt item: #704 of 872 id: fcis-3736 author: Zhang, Guoli title: Crowd Counting Based on Context-Aware and Multi Scale Feature Fusion date: 2022 words: 2298 flesch: 60 summary: Each CMFM consist of multi-scale feature extraction module (MEM) and context-aware feature extraction module (CEM). Multi-scale feature extraction module (MEM) Inspired by ASPP keywords: context; counting; crowd; feature; module; network; scale cache: fcis-3736.pdf plain text: fcis-3736.txt item: #705 of 872 id: fcis-3740 author: Wu, Chenyanzhe title: Application of eye movement tracking technology in web design date: 2022 words: 2256 flesch: 53 summary: China Abstract: Eye movement tracking technology is an emerging technology in recent years and has been widely used in many fields. This paper mainly introduced the application and analysis of eye movement tracking technology in various fields at home and abroad. keywords: eye; eyeball; human; movement; reading; research; technology; tracking cache: fcis-3740.pdf plain text: fcis-3740.txt item: #706 of 872 id: fcis-3743 author: Song, Xueyan title: Research on Application of Mathematical Modeling Based on Matrix Theory date: 2022 words: 2153 flesch: 48 summary: Matrix theory is the core content of higher algebra, and many ideas and methods in matrix theory greatly enrich the algebraic theory of mathematics. Therefore, the application of matrix operation in the construction of matrix theory is very common, and it has become a basic tool to study matrix problems. keywords: application; mathematical; matrix; modeling; research; theory cache: fcis-3743.pdf plain text: fcis-3743.txt item: #707 of 872 id: fcis-3744 author: Li, Jiahang title: Research on Interactive System of Movie Subtitle Speech Based on Machine Learning Technology date: 2022 words: 2210 flesch: 42 summary: The processing process of speech recognition system is that the user inputs a speech signal through a speech input device at first. With the development of speech technology and natural language understanding, speech interaction system has become a hot research field. keywords: movie; recognition; speech; subtitle; system; voice cache: fcis-3744.pdf plain text: fcis-3744.txt item: #708 of 872 id: fcis-3746 author: Cheng, Lang; Chen, Changzhong; Liu, Xin; Luo, Qi title: Design and optimization of an order killing system date: 2022 words: 1397 flesch: 58 summary: Design and optimization of high concurrency Web e-commerce system [J]. System functions design (1) System login: user name password verification and other functions. keywords: kill; order; product; second; system; user cache: fcis-3746.pdf plain text: fcis-3746.txt item: #709 of 872 id: fcis-3751 author: Wang, Rong; Liu, Yongchun title: Trajectory Tracking of Mobile Robot Based on Improved Hierarchical Sliding Mode Control date: 2022 words: 3712 flesch: 58 summary: Lee et al. proposed to apply sliding mode control to wheeled mobile robot, so that the mobile robot can run steadily on the target trajectory. [4] Lee J H, Lin C, Lim H, et al: Sliding mode control for trajectory tracking of mobile robot in the RFID sensor space, International Journal of Control, Automation and Systems,Vol. 7 (2009) No.3, p. 429-435. keywords: control; mobile; mode; robot; system cache: fcis-3751.pdf plain text: fcis-3751.txt item: #710 of 872 id: fcis-3754 author: Wang, Chenyu title: Pattern Classification of Stock Price Moving date: 2022 words: 9376 flesch: 62 summary: In 2016, Lahmiri S has discussed how to examine the co-movement of stock data by implementing hierarchical clustering but hierarchical algorithm is considered to be not very useful in clustering of stock price moving data Ghadhab I have come up a conclusion in his research in 2016 that the trading volume, or say volume of transaction can only review the notability of each stock but not the tendency, and for this reason, the project uses stock price moving data to cluster different stocks [4]. keywords: algorithm; analysis; canopy; clustering; clusters; data; means; means algorithm; moving; number; price; stock cache: fcis-3754.pdf plain text: fcis-3754.txt item: #711 of 872 id: fcis-3931 author: Wang, Peihong title: Research on firewall technology and its application in computer network security strategy date: 2022 words: 4180 flesch: 37 summary: 3. Firewall technology Firewall is a control device for two different networks to realize mutual access, and it is an important security device for network security to realize access control of private network and public network according to the artificially formulated control policy. After implementing address translation, the internal structure of the protected network can be hidden and network security can be improved to some extent. keywords: access; application; computer; firewall; host; information; network; security; technology cache: fcis-3931.pdf plain text: fcis-3931.txt item: #712 of 872 id: fcis-3932 author: Huang, Yantai title: Research on the teaching of intelligent and networked electrical control course driven by projects date: 2022 words: 1662 flesch: 45 summary: The key issues of this project mainly include the following: how to select a suitable applied project, which should have practical application value and include relevant knowledge of the course; How to reasonably design theory and practice courses, mobilize students' initiative, and use extracurricular time to participate in project design. The key to the successful reform of the course to meet the requirements 48 of applied undergraduate is the selection of applied projects. keywords: control; course; project; teaching cache: fcis-3932.pdf plain text: fcis-3932.txt item: #713 of 872 id: fcis-3933 author: Xiang, Daodong title: Research on character recognition technology based on deep learning date: 2022 words: 1977 flesch: 49 summary: Research on the application of OCR character recognition based on deep learning in the banking industry The input is character image, and the output is recognition result, so the whole workflow becomes very simple. keywords: character; image; layer; network; recognition cache: fcis-3933.pdf plain text: fcis-3933.txt item: #714 of 872 id: fcis-4085 author: Cai, Jiaowu; Liu, Peng; Li, Liangyu title: Pipeline gas leakage early warning system based on wireless sensor network date: 2022 words: 3350 flesch: 51 summary: The data acquisition and storage module consist of sensors, intelligent gateway and MySQL database to complete the real-time 54 collection and storage function of household pipeline gas data; the prediction module is fuzzy-Random forest model is responsible for dynamically predicting the gas leakage level of household pipeline. Therefore, the above six types of data are selected as the monitoring indicators of the dynamic early warning model of household pipeline gas leakage, based on the Code for Design of Urban Gas (GB50028-2006) and the index number and value range of the sensors used, see Table 1. keywords: algorithm; data; forest; forest model; gas; gas leakage; leakage; model; network; pipeline; prediction cache: fcis-4085.pdf plain text: fcis-4085.txt item: #715 of 872 id: fcis-4086 author: Wang, Xudong title: Research on news text classification based on RCNN date: 2022 words: 2580 flesch: 52 summary: Traditional machine learning requires a lot of pre- processing work in text classification, and when text features are extracted, more shallow features are obtained. However, text classification based on traditional machine learning algorithms encountered bottlenecks in the development process, and after deep learning, a multi- level neural network, was introduced, it was soon widely used in natural language processing problems, making many branches of the field develop further, and now deep learning is the mainstream model in the field of text classification. keywords: classification; feature; learning; models; text; word cache: fcis-4086.pdf plain text: fcis-4086.txt item: #716 of 872 id: fcis-4087 author: Chen, Wei title: Design and implementation of Pedestrian detection based on Zynq APSoc date: 2022 words: 1729 flesch: 54 summary: The input and output channels and hardware algorithm modules of video data are set up. As shown in the figure below, we see that VDMA has an AXI4 Memory Map interface for reading and writing video data to memory, an AXI4-Lite interface for reading VDMA status and configuring VDMA parameters, and an AXI4-Stream interface, For video input and output. keywords: data; display; image; output; ov5640; processing; system; video cache: fcis-4087.pdf plain text: fcis-4087.txt item: #717 of 872 id: fcis-4145 author: Huang, Yuxin title: Research on Lovelorn Emotion Recognition Based on Ernie Tiny date: 2023 words: 2815 flesch: 47 summary: In order to address the problem that few existing sentiment analysis studies detect love loss emotion texts, the author crawled love loss emotion texts on the social media platform Weibo, combined with normal sentiment reviews as dataset, and the ERNIE Tiny model was trained to recognize lovelorn emotion texts, which can effectively classify texts containing love-loss emotion from ordinary non-love-loss texts, and finally achieve satisfactory results. At the same time, there are fewer studies on the psychological emotion analysis for the emotion of lost love, so this paper focuses on 68 the study of the recognition of the lovelorn emotion using deep learning model. 3.2. keywords: analysis; classification; emotion; ernie; learning; model; sentiment; text cache: fcis-4145.pdf plain text: fcis-4145.txt item: #718 of 872 id: fcis-4146 author: Jiang, Qisheng title: A Financial Handwritten Digit Recognition Model Based on Artificial Intelligence date: 2023 words: 3850 flesch: 40 summary: Email: jqsxiaoer@163.com Abstract: Handwritten digit recognition is a kind of image information classification problem through optical character analysis. Based on the broad application prospect of handwritten digit recognition in finance, this paper focuses on the research and analysis of the handwritten digit recognition model for its insufficient accuracy, low performance, and other problems. keywords: accuracy; digit; learning; model; network; rate; recognition; technology cache: fcis-4146.pdf plain text: fcis-4146.txt item: #719 of 872 id: fcis-4147 author: Ren, Jie; Jiang, Kuosheng; Guo, Hui; He, Dongyang; Hu, Zhongwen; Yin, Ziyang title: Quantitatively evaluate the cylindricity of Large size pipe fitting via laser displacement sensor and Digital twin technology date: 2023 words: 4585 flesch: 49 summary: Frontiers in Computing and Intelligent Systems ISSN: 2832-6024 | Vol. 2, No. 2, 2022 75 Quantitatively evaluate the cylindricity of Large size pipe fitting via laser displacement sensor and Digital twin technology Jie Ren1,2 *, Kuosheng Jiang1,2,3,4, a, Hui Guo5, b, Dongyang He1,2, c, Zhongwen Hu1,2, d, Ziyang Yin1,2, e 1 State Key Laboratory of Mining Response and Disaster Prevention and Control in Deep Coal Mines, Huainan 232001, China 2 School of Mechanical Engineering, Anhui University of Science and Technology, Huainan 232001, China 3Shaanxi Steam Huainan Special Purpose Automobile Co., LTD., Huainan 232001, China 4Key Laboratory of Conveyance Equipment, Ministry of Education, Nanchang 330013, China 5Avic Aircraft Landing Gear Co. LTD, Changsha 410200, China * After positioning by the machine vision camera system, the servo system and laser displacement sensor scan the large-size pipe fitting layer by layer and establish the information interaction between physical space and virtual space through digital twinning technology. keywords: center; circle; cylindricity; detection; digital; displacement; laser; measurement; method; point; sensor; system cache: fcis-4147.pdf plain text: fcis-4147.txt item: #720 of 872 id: fcis-4465 author: Deng, Jianyang; Lin, Yijia title: The Benefits and Challenges of ChatGPT: An Overview date: 2023 words: 1854 flesch: 48 summary: AI can be used to solve complex problems, such as medical diagnosis, autonomous vehicles, and natural language processing. Since then, AI has continued to rapidly advance, with breakthroughs in machine learning, natural language processing, and robotics. keywords: chatgpt; data; language; learning cache: fcis-4465.pdf plain text: fcis-4465.txt item: #721 of 872 id: fcis-4601 author: Yi, Ronghua title: Research on the defense mechanism based on FDIA in smart grid date: 2023 words: 4067 flesch: 40 summary: The protection method can be found to provide great help for transient stability of power systems. Impact of FDIA on security control In terms of power system security control, the consequences of the attack can be divided into the impact on system observability and controllability and the impact on security stability. keywords: attack; control; data; defense; detection; fdia; grid; information; power; security; state; system cache: fcis-4601.pdf plain text: fcis-4601.txt item: #722 of 872 id: fcis-4602 author: Tian, Fengyuan title: Closed Trajectory Optimization for Aerial Base Station: An Energy Efficiency Design date: 2023 words: 6060 flesch: 59 summary: Keywords: UAV communication; Aerial base stations; Trajectory optimization. For the fly-over scheme, the distance of optimal UAV trajectory is even shorter. keywords: communication; consumption; energy; fly; flying; hover; ieee; problem; time; trajectory; uav cache: fcis-4602.pdf plain text: fcis-4602.txt item: #723 of 872 id: fcis-4898 author: Lu, Yinyin; Huang, Delu; Wang, Le; Huang, Xu; Xu, Haichao title: Research on Intelligent Sensing Technology of Traffic Volume in Yancheng Inland Trunk Waterway date: 2023 words: 2108 flesch: 37 summary: Database Design of Channel Flow Monitoring System Data Class Data Set Data Sources Basic Data Channel basic data, ship basic data, route basic data, etc. Port and Shipping Center Statist ical Data Ship traffic volume data, channel throughput data, hydrological scale data, etc. AIS、Lidar Video Data Video camera basic data, video data, etc. Monitorin g Video Basic database includes static data such as channel basic data, ship basic data and route basic data, which is mainly used to provide basic data support for application layer. keywords: algorithm; channel; data; identification; monitoring; navigation; ship; traffic; video cache: fcis-4898.pdf plain text: fcis-4898.txt item: #724 of 872 id: fcis-5200 author: Liu, Luming; Yang, Qingq; Zhu, Zewei title: Research and application of digital technology of film coating equipment date: 2023 words: 2936 flesch: 34 summary: In coating (coating) equipment, with signal, data technology to produce equipment data acquisition, the operation of energy and raw materials consumption, into the library for real-time monitoring, strictly control the quality of products, improve the automation of production process, improve production efficiency and promote product quality, promote the improvement of automation level and core competitiveness. (2) Transmission and communication mode of coating process data. keywords: analysis; coating; data; equipment; monitoring; process; production; system; technology cache: fcis-5200.pdf plain text: fcis-5200.txt item: #725 of 872 id: fcis-5201 author: Liu, Yan; Zhang, Meina title: Design and Implementation of Online Education Platform Based on ThinkPHP Abstract date: 2023 words: 2691 flesch: 50 summary: At present, the research direction of online education in developed countries such as the United States, Britain and Japan is online education platform. The significance of online education platform depends on the equality of educational resources. keywords: development; education; information; management; platform; students; system; teachers; users cache: fcis-5201.pdf plain text: fcis-5201.txt item: #726 of 872 id: fcis-5202 author: Yu, Li; Wu, Shenghong; Feng, Yetao; Zhao, Chenlei title: Basic principle of cuckoo optimization algorithm date: 2023 words: 1844 flesch: 59 summary: The cuckoo algorithm can be applied to more data analysis and processing, providing a basic principle for cuckoo algorithm data processing, and laying a solid foundation for the improvement of cuckoo algorithm. China Abstract: This paper introduces the basic principle of cuckoo algorithm from cuckoo's habits. keywords: algorithm; cuckoo; host; nest; optimization; step cache: fcis-5202.pdf plain text: fcis-5202.txt item: #727 of 872 id: fcis-5203 author: Zhu, Xiaochen title: Compute offloading solution to maximize server rewards date: 2023 words: 4529 flesch: 54 summary: The research does not aim to minimize computing delay and energy consumption, but to maximize the reward of edge computing servers. The simulation results show that when solving discrete offloading problems, the improved sine cosine algorithm has the best performance. keywords: algorithm; computing; edge; offloading; problem; sca; server; solution; terminal cache: fcis-5203.pdf plain text: fcis-5203.txt item: #728 of 872 id: fcis-5204 author: Fang, Wangming title: A Review of Traditional Dehazing Methods for Foggy Images date: 2023 words: 3104 flesch: 43 summary: Although deep learning techniques have made significant progress in image dehazing, the effectiveness and role of traditional image dehazing methods are still fundamental and have their unique advantages. Keywords: Atmospheric scattering models; Contrast enhancement; Image dehazing; Image enhancement. keywords: dehazing; enhancement; fog; fusion; image; method cache: fcis-5204.pdf plain text: fcis-5204.txt item: #729 of 872 id: fcis-5205 author: Ma, Ruoxin; Xu, Rui; Sun, Yutao title: Wise rescue, safety accompanying: -- Dawning Intelligent rescue system date: 2023 words: 2657 flesch: 41 summary: System functions Based on the understanding and analysis of the cloud real- time monitoring traffic accident emergency rescue system, the system is divided into the following five main functions: Accurate positioning: The Beidou navigation and positioning system can provide rescuers with the precise location of the accident, and provide the specific position coordinate information in the accident message, so as to facilitate the understanding of the source of the accident. The latest multifunctional recorder on the market also aims to improve user experience, increase intelligent voice, navigation and other functions, and has not been applied in traffic accident emergency rescue. keywords: accident; data; emergency; information; rescue; system; traffic; vehicle cache: fcis-5205.pdf plain text: fcis-5205.txt item: #730 of 872 id: fcis-5208 author: Jiang, Yuchen title: A review of routing algorithms for underwater wireless sensor networks date: 2023 words: 2134 flesch: 46 summary: routing protocol is proposed in to mitigate the drawbacks of EEDBR.WDFAD-DBR solves the gap problem by considering the depth difference of two-hop nodes and reduces the energy consumption by designing forwarding area and neighbor node prediction. Routing protocols based on intelligent optimization algorithms In , a routing protocol named EECRP based on genetic algorithms that view sensor nodes as genes and routing paths as chromosomes was proposed. keywords: energy; networks; nodes; protocol; routing; sensor; wireless cache: fcis-5208.pdf plain text: fcis-5208.txt item: #731 of 872 id: fcis-5209 author: Li, Qingyu; Zhang, Yujun title: Improved Text Matching Model Based on BERT date: 2023 words: 3088 flesch: 57 summary: With the rapid development of deep learning, a large number of text matching models based on deep learning have emerged, which can be roughly divided into three types: representation based method, interaction based method and pretraining language model based method. However, the text semantic information obtained by fine-tuning specific text matching tasks using BERT model alone is insufficient, Therefore, based on this problem, this paper proposes a method based on pretraining BERT model fusion of BiLSTM and multi-scale CNN to remodel the text matching task, further extract global semantic information and local semantic information to improve the accuracy of text matching. keywords: bert; bilstm; information; layer; matching; method; model; text cache: fcis-5209.pdf plain text: fcis-5209.txt item: #732 of 872 id: fcis-5210 author: Pu, Kang title: Intellectual property protection for AI algorithms date: 2023 words: 3473 flesch: 35 summary: As the core technology of artificial intelligence, artificial intelligence algorithms have the ability to train and learn human-like self-training, and have become one of the most concerned fields. In recent years, there has also been an increasing discussion of artificial intelligence algorithms. keywords: algorithms; development; intelligence; intelligence algorithms; patent; protection cache: fcis-5210.pdf plain text: fcis-5210.txt item: #733 of 872 id: fcis-5211 author: Zhou, Lv title: A Vehicle Service Migration Strategy Algorithm in 5G NR-V2X date: 2023 words: 6096 flesch: 57 summary: Such an interruption is intolerable for vehicle in V2X. Therefore, it is necessary to consider the issue of service migration. Keywords: Mobile edge computing; Vehicle edge computing; Service migration; Markov Decision Process; Delay; Energy consumption; Deep reinforcement learning. keywords: algorithm; computing; consumption; cost; energy; migration; model; network; paper; roadside; rsu; service; v2x; value; vehicle cache: fcis-5211.pdf plain text: fcis-5211.txt item: #734 of 872 id: fcis-5212 author: Zhang, Mengyu; Li, Chunqing title: Research on Intelligent Detection System for Predicting Membrane Pollution date: 2023 words: 2011 flesch: 51 summary: The key problem restricting the development of MBR is membrane pollution. This paper summarizes the main causes of membrane pollution and common treatment methods, and puts forward a new method of membrane pollution prevention - intelligent detection system. keywords: data; detection; membrane; module; pollution; sludge; system; treatment cache: fcis-5212.pdf plain text: fcis-5212.txt item: #735 of 872 id: fcis-5213 author: Zhang, Run title: Three-dimensional positioning based on TOA combining acoustic signal and optical signal date: 2023 words: 3331 flesch: 55 summary: Due to the localization accuracy plays a key role in underwater wireless localization,so many practical localization methods was put forward,such as Time of Arrival (TOA)–, Time Difference of Arrival (TDOA),, Received Signal Strength (RSS)–,Angle of Arrival (AOA), ,and hybrid localization–. In an outdoor environment,the unknown node (UN) can be located with highly accuracy from the Global Positioning System (GPS),or from BeiDou Navigation Satellite System. Therefore, underwater wireless sensor networks can be well used for locating unknown nodes. keywords: anchor; distance; node; positioning; signal; underwater; vol; wireless cache: fcis-5213.pdf plain text: fcis-5213.txt item: #736 of 872 id: fcis-5214 author: Wei, Lingtao title: Communication Efficient Federated Personalized Recommendation date: 2023 words: 3497 flesch: 49 summary: However, recommendation systems require users' personal information, and centralized collection and processing of user data may lead to serious privacy risks. Recommender systems need to collect user data to perform analytical modeling to analyze user preferences in order to provide services to users. keywords: aggregation; data; grouping; model; performance; recommendation; training; user cache: fcis-5214.pdf plain text: fcis-5214.txt item: #737 of 872 id: fcis-5215 author: Tian, He; Zhang, Jing; Yang, Li; Tang, Yongli; Zha, Chunming title: Multi-party Privacy Set Intersection protocol with an Untrusted Cloud Server date: 2023 words: 6525 flesch: 70 summary: In [26,27], authours proposed privacy set intersection protocols supporting multiple parties respectively, but their computation and communication are done by each party, and when the party's equipment is limited, it is not possible to securely use cloud services to assist the computation. i c X c i R R R R R R R R R R R R R R R R   keywords: cloud; intersection; protocol; psi; r r; r x; set cache: fcis-5215.pdf plain text: fcis-5215.txt item: #738 of 872 id: fcis-5218 author: Wu, Wei title: Identification of tea leaf diseases based on deep transfer learning date: 2023 words: 2614 flesch: 47 summary: This prior knowledge can be very quickly transferred to the recognition task of tea leaf disease images. Frontiers in Computing and Intelligent Systems ISSN: 2832-6024 | Vol. 2, No. 3, 2022 75 Identification of tea leaf diseases based on deep transfer learning Wei Wu Taishan University, Tai'an 271000, keywords: function; leaf; learning; loss; model; tea; tea leaf cache: fcis-5218.pdf plain text: fcis-5218.txt item: #739 of 872 id: fcis-5314 author: Guo, Zhenxing; Mo, Li title: Robot path planning based on improved genetic algorithm date: 2023 words: 2112 flesch: 55 summary: To solve the problem of robot path planning, researchers have put forward a variety of methods, among which the intelligent optimization algorithm is more widely used, including genetic algorithm In genetic algorithm, the value of crossover probability and genetic probability can be between 0 and 1. keywords: algorithm; crossover; path; planning; probability cache: fcis-5314.pdf plain text: fcis-5314.txt item: #740 of 872 id: fcis-5315 author: Chen, Xue title: Risk-based Access Control Model for Hospital Information Systems date: 2023 words: 2340 flesch: 50 summary: Part 2 introduces the current status of access control research at home and abroad, and analyzes the research progress and shortcomings of access control models. There is an increase in scholarly research on access control models, but there is less research on risk-based access control in HIS. keywords: access; control; data; information; model; num; risk cache: fcis-5315.pdf plain text: fcis-5315.txt item: #741 of 872 id: fcis-5316 author: Yu, Houhui title: Application of blockchain technology in the renovation management of old neighborhoods date: 2023 words: 2857 flesch: 37 summary: 6. Conclusion Applying blockchain technology to the project management platform of old neighborhood renovation, on the one hand, the information of personnel, materials and transaction amount is put on the chain through data encryption, which reduces unnecessary cost expenditure; on the other hand, in view of blockchain's characteristics of reliability and information non-tamper ability, all aspects of old neighborhood renovation process become clearer and more transparent, which increases the credibility of the government and at the same time reduces the public's consideration of old It also reduces people's worries about the quality of old housing renovation. Frontiers in Computing and Intelligent Systems ISSN: 2832-6024 | Vol. 2, No. 3, 2022 85 Application of blockchain technology in the renovation management of old neighborhoods Houhui Yu Yunnan University of Finance and Economics, School of Information, Kunming 650221, China yhouhui@163.com. keywords: blockchain; data; hash; information; process; project; technology; transaction; transformation cache: fcis-5316.pdf plain text: fcis-5316.txt item: #742 of 872 id: fcis-5317 author: Huang, Xuan; Shen, Hongping; Liu, Binhui; Yin, Xiaojun; Peng, Qi title: Research on High Reliable Multimode Wireless Communication Technology for UAV date: 2023 words: 3716 flesch: 48 summary: This method can effectively improve the reliability and efficiency of UAV data transmission. By dynamically adjusting the target coding rate through the target channel parameters, the bandwidth utilization of wireless communication links can be improved. keywords: communication; data; data packets; image; link; target; transmission cache: fcis-5317.pdf plain text: fcis-5317.txt item: #743 of 872 id: fcis-5318 author: Tian, Xun title: Trust Evaluation of Doctor Behavior Based on GCN Network in Medical Big-Data Access Control date: 2023 words: 2196 flesch: 52 summary: In this paper, we propose a graphical convolutional neural network to detect the access behavior of doctors in medical big data. In this paper, we propose a graphical convolutional neural network to model the access behavior of doctors in medical big data and perform trust evaluation, so as restrict such doctors or behaviors. keywords: access; big; control; data; doctors; health; privacy; trust cache: fcis-5318.pdf plain text: fcis-5318.txt item: #744 of 872 id: fcis-5411 author: Chen, Yang title: Improvement of Association Algorithm Based on Matrix Optimization date: 2023 words: 2619 flesch: 60 summary: When putting the newly generated item set group into the queue, if the number of items sets in the item set group is less than 2, it will be discarded, which has a certain pruning effect and saves a certain amount of time. Keywords: Frequent itemsets; Boolean matrix; Simplified matrix; Optimal connection. keywords: algorithm; matrix; set;   cache: fcis-5411.pdf plain text: fcis-5411.txt item: #745 of 872 id: fcis-5412 author: Luo, Sifeng; Huang, Xi title: A Lightweight Neural Network for Palm Vein Recognition date: 2023 words: 3592 flesch: 46 summary: Tarawneh et al.[4] used pre-trained CNNs such as AlexNet, VGG-16 and VGG-19 for palm vein image feature extraction. The traditional designs of palm vein feature extraction and recognition are summarized into 3 ways. keywords: feature; image; lightweight; module; network; palm; palm vein; recognition; vein cache: fcis-5412.pdf plain text: fcis-5412.txt item: #746 of 872 id: fcis-5413 author: Ding, Jingru title: Review of Research on Vehicle Routing Problem and Related Algorithms date: 2023 words: 2535 flesch: 40 summary: China Abstract: This paper briefly introduces the relevant theories and wide applications of vehicle routing problem, and then summarizes some common exact algorithms and heuristic algorithms for solving the vehicle routing problem. Variants of vehicle routing problem With the continuous development of real logistics, the basic vehicle routing problem is not enough to meet all needs. keywords: distribution; problem; routing; solution; vehicle; vehicle routing cache: fcis-5413.pdf plain text: fcis-5413.txt item: #747 of 872 id: fcis-5414 author: Guan, Zhihao title: Object Detection in Junk Image Based on SSD Model date: 2023 words: 4940 flesch: 53 summary: For example, in recent years, RSSD has designed a rainbow connection method that uses pooling and deconvolution operations at the same time to perform feature fusion on different feature layers. Abstract: This paper first introduces the background and significance of the direction in target detection, and introduces other target detection methods besides SSD. keywords: algorithm; bounding; box; detection; feature; information; layer; network; object; ssd; target cache: fcis-5414.pdf plain text: fcis-5414.txt item: #748 of 872 id: fcis-5508 author: Wang, Yalan; Wu, Zhen title: A Side-Channel Analysis on the TALE date: 2023 words: 3583 flesch: 57 summary: In side-channel analysis (SCA), template attack is considered to be the most effective analysis method, and traditional template analysis are now gradually being replaced by machine learning-based template attack due to low computational efficiency. Traditional side-channel analysis include SPA, CPA, DPA, template attack, and timing attack, and with the rapid development of machine learning techniques, support vector machines, random forests, and neural networks are increasingly used to improve side- channel efficiency. keywords: algorithm; analysis; attack; channel; feature; key; leakage; message; points; tale; template cache: fcis-5508.pdf plain text: fcis-5508.txt item: #749 of 872 id: fcis-5509 author: Chang, Yulong; Zhu, Youchan; Cui, Kaili; Guan, Fujun; Li, Zheng title: Location of Scene Text Based on Yolov7 date: 2023 words: 2826 flesch: 64 summary: Keywords: Text detection; YOLOv7; Deep learning. However, the success of OCR system is limited to scanning the text in the document, and the recognition rate of scene text is not high. keywords: bounding; conv; detection; elan; method; network; scene; text cache: fcis-5509.pdf plain text: fcis-5509.txt item: #750 of 872 id: fcis-5510 author: Wang, Jinjin; Qin, Yang; Shi, Jiahao; Luo, Jiachen; Huang, Guo; Lu, Jiaqi title: Research on Algorithm of Video Analysis System Based on Text Error Correction date: 2023 words: 2798 flesch: 52 summary: Conclusion This paper studies video analysis based on text error correction from three aspects: speech segmentation and speech to text, text recognition and error correction, text to speech and video speech synthesis. MEdist's phased efficient algorithm, DAEC algorithm and I-Zhrtvc algorithm are applied to video analysis research based on text error correction. keywords: accuracy; algorithm; audio; correction; error; speech; text; video; voice cache: fcis-5510.pdf plain text: fcis-5510.txt item: #751 of 872 id: fcis-5958 author: Zhuo, Chen title: Prediction of Telecom Customer Churn Based on MIPCA-XGBoost Method date: 2023 words: 3587 flesch: 52 summary: Abstract: In order to solve the problem that the nonlinear information of data in the field of telecom customer churn prediction is not fully used, or even ignored, which leads to inaccurate prediction, this paper introduces the mutual information feature selection method (MIPCA) to filter the features and reduce the dimensions of customer data, and proposes an XGBoost method based on the mutual information feature selection method(MIPCA-XGBoost), which improves the accuracy of the prediction results. Although the above research has made important contributions to the research on customer churn prediction in the fields of aviation, life insurance, e-commerce and so on, it does not mine the important features of the data set, resulting in information redundancy and even dimension disaster [5], which will have an impact on the customer churn prediction in the telecommunications industry and reduce its prediction efficiency and accuracy. keywords: churn; customer; data; feature; information; method; mipca; prediction; set; xgboost cache: fcis-5958.pdf plain text: fcis-5958.txt item: #752 of 872 id: fcis-5962 author: Liao, Zhihong; Song, Jinyuan; Yang, Jingyu title: Research on Wildlife Trade Based on SARIMA and Multiple Regression date: 2023 words: 5091 flesch: 59 summary: To solve this problem, this paper first uses the 11 annual import and export volume of wildlife trade as the basic data, and collects the total global GDP as the indicator to measure the global economy, so as to build a multiple regression model to analyze the data relationship between the import and export volume of global wildlife trade and the total global GDP, and according to the relationship between the three, Answer whether wildlife trade should be banned for a long time and its impact on the global economy. The results are as follows: Gobal GDP = −4620 + 2.3344 ∗ time − 6.31 ∗ 10−4 ∗ In − 7.96 ∗ 10−4 ∗ Out According to the analysis of the above formula, the global GDP shows a typical proportional promotion relationship with time, while there is a typical negative correlation with global wildlife trade, that is, wildlife trade has an inhibitory effect on the growth of global GDP. keywords: analysis; data; export; global; import; model; paper; trade; trade market; wildlife trade cache: fcis-5962.pdf plain text: fcis-5962.txt item: #753 of 872 id: fcis-6016 author: Zhong, Jingran; He, Bi; Geng, Chuanzhi title: Development of Electric Power Networks Inspection Information Management System Based on MapWorld API date: 2023 words: 1892 flesch: 50 summary: This paper uses this technology to design and develop a set of electric power patrol information management system. At the same time, with the development of artificial intelligence and big data technology, as well as the introduction and use in this system, the analysis ability of the system will be further improved, and the value of electric power patrol data will be better excavated, which is the next development direction of this system. keywords: data; information; inspection; management; patrol; system cache: fcis-6016.pdf plain text: fcis-6016.txt item: #754 of 872 id: fcis-6017 author: Liu, Simin title: Study on Typical Aerodynamic Faults of Variable Pitch Wind Turbine date: 2023 words: 3061 flesch: 54 summary: Keywords: Wind turbine; System vibration faults; Aerodynamic characteristics. Modeling method of typical aerodynamic characteristics The key point of analyzing the typical aerodynamic characteristics of wind turbines is to determine whether the fluctuation of aerodynamic characteristics will cause resonance phenomenon. keywords: blade; effect; frequency; shadow; tower; tower shadow; wind; wind shear cache: fcis-6017.pdf plain text: fcis-6017.txt item: #755 of 872 id: fcis-6018 author: Chen, Duiyu; Chen, Jing; He, Chengxu title: Unsupervise contrastive learning person re-identification Method based on Transfomer date: 2023 words: 3621 flesch: 56 summary: However, the spatial resolution of image features is reduced by down-sampling operation, such as pooling, compromising discrimination ability to identify similar looking objects. [12] Z. Zhong, L. Zheng, Z. Luo, S. Li, and Y. Yang, “Learning to adapt invariance in memory for person re-identification,” IEEE Trans. keywords: cluster; cnn; dictionary; feature; identification; image; instance; learning; memory; person; reid; transformer cache: fcis-6018.pdf plain text: fcis-6018.txt item: #756 of 872 id: fcis-6019 author: Wei, Jingyu title: A Survey of Face Recognition Methods Based on Mask Region Restoration Algorithm date: 2023 words: 3020 flesch: 46 summary: In this paper, the existing mask region repair algorithms at home and abroad are classified and summarized, mainly including mask occlusion face recognition based on robust occlusion, mask occlusion face recognition based on sparse representation classification and mask occlusion face recognition based on neural network. Mask face recognition method based on cnn and transformer mixed model. keywords: face; face recognition; image; mask; method; model; occlusion; recognition; representation cache: fcis-6019.pdf plain text: fcis-6019.txt item: #757 of 872 id: fcis-6020 author: Huang, Ruifan; Xu, Huifei title: Intelligent Diagnosis of Alzheimer's disease date: 2023 words: 4990 flesch: 55 summary: Based on this, this paper uses decision tree model and random forest model to classify the data, and constructs model accuracy indexes: confusion matrix, acc, etc. so as to judge the advantages and disadvantages of the classification model. b1225604713@qq.com Abstract: In this paper, we combine the knowledge of decision tree model and K-means clustering algorithm with knowledge of statistics to solve the problems of Diagnosis of Alzheimer's disease using brain structure. keywords: alzheimer; data; disease; figure; indicators; model; paper; samples; set; tree cache: fcis-6020.pdf plain text: fcis-6020.txt item: #758 of 872 id: fcis-6021 author: Sun, Lin title: Multimodal Emotion Recognition and Fluctuation: A Study on Sentiment Analysis of Online Public Opinion date: 2023 words: 3291 flesch: 40 summary: Conclusion Starting from the application value and challenges of sentiment analysis, this paper comprehensively analyzes the main steps and research methods of sentiment analysis and summarizes multimodal sentiment recognition methods suitable for analyzing public opinion in different forms, broadening research scope and the range of raw data that can be processed. For example, Pang and Lee et al. (2002) pioneered the application of machine learning to text sentiment analysis, comparing the effectiveness of different machine learning methods of Support Vector Machine, Naive Bayes, and Maximum Entropy for sentiment classification, and concluded that Support Vector Machine classifiers are best out of three. keywords: analysis; data; emotion; fusion; learning; multimodal; opinion; recognition; sentiment; text cache: fcis-6021.pdf plain text: fcis-6021.txt item: #759 of 872 id: fcis-6022 author: Deng, Yuanfei title: Research on sentiment analysis methods for text-oriented data date: 2023 words: 5234 flesch: 39 summary: Text sentiment analysis focuses on how to enable computers to automatically identify, classify, annotate or extract the subjective content of human sentiment, emotions, opinions, evaluations, etc. expressed in natural language texts about a given subject or topic[9][10] The sentiment analysis is the evaluation of the public's opinions, emotionally recognized attitudes towards products, services, organizations and other objects[11] Text sentiment analysis refers to the process of analyzing, processing and extracting subjective texts with emotional overtones using natural language processing and text mining techniques[22] . keywords: analysis; classification; data; information; knowledge; language; learning; level; methods; research; sentiment; sentiment analysis; text; text sentiment cache: fcis-6022.pdf plain text: fcis-6022.txt item: #760 of 872 id: fcis-6023 author: Shang, Yuyan; Zhang, Chuanwu title: Simulation design and analysis of re modulation structure based on optical network date: 2023 words: 5400 flesch: 51 summary: Optical fiber communication systems have many advantages over metal-based communications. Abstract: With the development of information age, the optical fiber communication network has also been greatly developed, and a large number of optical fiber systems should be shipped. keywords: communication; fiber; frequency; modulation; network; noise; signal; system; technology; transmission; use; wavelength; wdm cache: fcis-6023.pdf plain text: fcis-6023.txt item: #761 of 872 id: fcis-6024 author: He, Xing title: Vehicle target detection algorithm based on yolov5 date: 2023 words: 3007 flesch: 49 summary: al.[6]borrowed the practice of global feature extraction of feature maps in SPPNet, and improved on the basis of R-CNN to propose Fast R-CNN, which solved the problem of cumbersome training of R-CNN and each training stage being independent of each other, and secondly solved the problem of requiring consistent input image size, and finally replaced the original SVM classifier with softmax. ACmix Hybrid Self-Attention Structure 58 Traditional convolution and self-attention modules actually share the same operation when projecting input feature maps by 1×1 convolution, and these two operations take up the main computational overhead. keywords: algorithm; detection; feature; image; model; network; size; target; yolov5 cache: fcis-6024.pdf plain text: fcis-6024.txt item: #762 of 872 id: fcis-6025 author: Yin, Ailiang; Li, Chunhao title: Research on Speech Emotion Recognition Analysis Based on Deep Learning date: 2023 words: 3627 flesch: 46 summary: For network models such as Resnet for image processing, the data input to the network appears to pass through 64 or more convolutional kernels, and the convolutional kernel size is larger, such as 7× 7 or 5× 5 convolutional kernels to speed up the training efficiency. The importance of speech emotion recognition in the field of artificial intelligence is self-evident. keywords: att; block; emotion; layer; model; network; recognition; res; speech cache: fcis-6025.pdf plain text: fcis-6025.txt item: #763 of 872 id: fcis-6026 author: Yan, Yifan; Yu, Weiwei title: Cross-age face synthesis based on conditional adversarial autoencoder date: 2023 words: 5223 flesch: 56 summary: Abstract: Face aging aims to render face images with desired age attribute. Concatenating with the age labels ,they are mapped to the manifold– generating a series of face images. keywords: age; aging; characteristics; column; conditional; discriminator; face; identity; images; information; method; skin cache: fcis-6026.pdf plain text: fcis-6026.txt item: #764 of 872 id: fcis-6027 author: Wang, Yu; Guo, Li; Zhang, Yanrui; Ma, Xinyue title: Research on CSI 300 Stock Index Price Prediction Based On EMD-XGBoost date: 2023 words: 4133 flesch: 62 summary: China Abstract: The combination of artificial intelligence techniques and quantitative investment has given birth to various types of price prediction models based on machine learning algorithms. Analysis of evaluation indicators After training the LSTM and XGBoost algorithm models optimally using the empirical modal decomposition method, the evaluation metrics are compared with the unoptimized evaluation metrics as shown in the following figure. keywords: model; prediction; t t; xgboost cache: fcis-6027.pdf plain text: fcis-6027.txt item: #765 of 872 id: fcis-6028 author: Zhang, Yue; Du, Zhibo title: Optimizing WinAFL for Image Parsing Engine Vulnerability Discovery in PDF Readers date: 2023 words: 2841 flesch: 55 summary: In this paper, to solve the problem of high blindness in fuzzing for PDF files by the fuzzing tool WinAFL, we propose a targeted fuzzing scheme for the image parsing engine in PDF readers, optimize WinAFL purposefully, and conduct comparison experiments with the original WinAFL. In this paper, we optimize the variation method in WinAFL for the parsing engine of image format in PDF parser and propose a targeted fuzzing scheme for the image parsing engine in PDF reader to reduce the blindness of the WinAFL fuzzer for fuzzing of PDF files, which considers the test cases that can explore new execution paths to be of high value. keywords: file; function; fuzzing; method; pdf; program; target; winafl cache: fcis-6028.pdf plain text: fcis-6028.txt item: #766 of 872 id: fcis-6029 author: Han, Yueming; Han, Fei; Xian, Darong title: Research on multi-Unmanned aerial vehicle joint delivery mission assignment based on multiple Alliance date: 2023 words: 2466 flesch: 49 summary: Under the control of the ground station, each drone according to the task allocation results, fly to different task target point material delivery tasks, for the number of drones, delivery tasks, prone to repeat tasks, mission omission, drones ineffective execution, in order to avoid more collaborative inefficiency, need to establish a strong coupling between delivery mission and drones, namely through the task allocation. Projection task assignment map As can be seen from the figure above, according to the UAV mobility, transportation capacity, endurance using rules for dynamic sorting, when delivery task more, also need to consider delivery mission importance, time node requirements, path length, eventually get more drone delivery mission set, the delivery mission assignment results can ensure that the task effectively, under the premise of optimal allocation of resources, can effectively save time cost, make efficient and flexible delivery on the battlefield keywords: agent; capability; delivery; multi; task; uav cache: fcis-6029.pdf plain text: fcis-6029.txt item: #767 of 872 id: fcis-6030 author: Li, Yi title: Text-to-Classic: A Diffusion Method for Classical Art Generation Based on Text date: 2023 words: 3547 flesch: 59 summary: SemArt is a collection of classic art painting images. We propose a lightweight diffusion model Text-to-Classic(T2C) to synthesize classical art paintings according to text descriptions. keywords: art; attention; diffusion; image; model; synthesis; text cache: fcis-6030.pdf plain text: fcis-6030.txt item: #768 of 872 id: fcis-6031 author: Xin, Jiyuan; Du, Zhibo title: Template attack based on uBlock cipher algorithm date: 2023 words: 2660 flesch: 54 summary: In order to explore the application of template attack against uBlock cipher algorithm analysis attack, a template attack method against uBlock cipher algorithm is proposed. Keywords: Side channel attack; Template attack; uBlock algorithm. keywords: algorithm; attack; energy; information; key; model; template; ublock cache: fcis-6031.pdf plain text: fcis-6031.txt item: #769 of 872 id: fcis-6032 author: Chen, Yuanqi title: Research on speech style transfer algorithm combined with image processing perspective date: 2023 words: 2607 flesch: 48 summary: Finally, in view of the existing problems of speech style transfer, such as low naturalness of speech, high cost of modeling resources or easy to be disturbed by environment, some suggestions are provided for the development of speech style transfer technology. After a large number of scholars' long-term research and the continuous improvement of various algorithms, the technique of image style transfer has been relatively mature. keywords: image; network; speech; style; transfer; voice cache: fcis-6032.pdf plain text: fcis-6032.txt item: #770 of 872 id: fcis-6342 author: Dai , Chenchao; Qiang, Hongfu; Wang, Xueren title: Research on Divert and Attitude Control System Technology of Ballistic Missile Midcourse Maneuver Penetration Warhead date: 2023 words: 9076 flesch: 55 summary: [22] Yang Z. Research on solid attitude control system of KKV [D]. With the development of missile defense technology in the United States, the divert and attitude control system of KKV has been mature, so we can learn from the related technologies of interceptor divert and attitude control system, and then promote the development of penetration missile divert and attitude control system. keywords: attitude control; control system; development; divert; divert control; fig; leap; maneuver; penetration; pintle; research; solid; structure; technology; thrust; time; valve; warhead cache: fcis-6342.pdf plain text: fcis-6342.txt item: #771 of 872 id: fcis-6343 author: Hu, Sen; Zhang, Zhengquan; (Xiaokang) Mo, Kevin title: Homomorphic Encryption and its Application to Blockchain date: 2023 words: 2630 flesch: 53 summary: There are various forms of homomorphic encryption and they can be classified into three categories: partially homomorphic encryption, hierarchical homomorphic encryption and fully homomorphic encryption. 1 School of Mathematical Sciences at USTC and Wu Lab of Mathematics of Chinese Academy of Sciences, Hefei, China 2 Beijing Data Institute, Beijing, China 3 National Innovation Research Institute (Xiamen), Inc, Xiamen, China Abstract: The concept, method, algorithm and application of the advanced field of cryptography, homomorphic encryption, as well as its application to the field of blockchain are discussed in this paper. keywords: data; encryption; homomorphism; key cache: fcis-6343.pdf plain text: fcis-6343.txt item: #772 of 872 id: fcis-6344 author: Liu, Qunjie; Wang, Hongxing title: UAV 3D path planning based on improved grey wolf optimization algorithm date: 2023 words: 2771 flesch: 53 summary: Keywords: UAV; Path planning; Grey wolf optimization algorithm; Cubic chaotic; Mutation operator. The literature[14]divides the search space into multiple dimensionality-reduced subspaces and proposes a parallel co-evolutionary grey wolf optimization algorithm to overcome the local optimality problem of the grey wolf optimization algorithm due to the increase in the dimensionality of the search space. keywords: algorithm; grey; optimization; path; planning; uav; wolf cache: fcis-6344.pdf plain text: fcis-6344.txt item: #773 of 872 id: fcis-6345 author: Liu, Mengjie; Zhen, Chenggang title: Power Supply Coal Consumption Prediction Model Based on Long and Short-term Memory Neural Network date: 2023 words: 1880 flesch: 58 summary: Research on energy efficiency characteristic indexes of coal power units and their benchmark values based on data mining. Keywords: Power supply coal consumption; MRMR; LSTM. keywords: coal; consumption; data; lstm; power cache: fcis-6345.pdf plain text: fcis-6345.txt item: #774 of 872 id: fcis-6346 author: Tan, Jingwen; Hu, Youxin; Luo, Jianqiu title: Social recommendation algorithm based on collaborative filter algorithms date: 2023 words: 2251 flesch: 46 summary: Recommendation algorithm 2.1. In recent years, many experts have found that the relationship between social network users can be seen as a link keywords: algorithm; community; filtering; paper; recommendation; social; user cache: fcis-6346.pdf plain text: fcis-6346.txt item: #775 of 872 id: fcis-6348 author: Yan, Dandan title: Research on Reinforcement Learning Explainable Strategies Based on Advantage Saliency date: 2023 words: 4818 flesch: 53 summary: In this paper, we use the perturbation-based saliency map method, propose the use of advantage function to replace the existing method of calculating state saliency, realize the combination of advantage function and perturbation-based saliency map. [8]utilize the difference of value function and policy vector between original state and perturbed state to generate saliency map, Iyer et al. keywords: action; advantage; agent; function; learning; saliency; state; value cache: fcis-6348.pdf plain text: fcis-6348.txt item: #776 of 872 id: fcis-6349 author: Zhang, Tao; Jiang, Yefeng title: Design and Realization of Surakarta Chess Game Program date: 2023 words: 3120 flesch: 66 summary: In this paper, bit sequences are used to represent the position of each chess point on the board, and two-bit sequences are used to represent chess pieces of different colors. The movable positions of chess pieces are divided into capture movement and non-capture movement. keywords: attack; chess; game; pieces; point; value cache: fcis-6349.pdf plain text: fcis-6349.txt item: #777 of 872 id: fcis-6350 author: Liu, Chanyi; Huang, Dan; Wang, Tao; Zhu, Tao title: Road Traffic Small Target Detection Algorithm Based on Lightweight YOLO V5 date: 2023 words: 2629 flesch: 50 summary: For target detection, many scholars have been improving the capability of target detection networks to achieve good detection results, Ren et al improved the SSD algorithm to enhance the detection capability of the network for obscured objects or small objects. YOLOv5 algorithm is the latest version of the current YOLO series detection algorithm, proposed by Ultralytics Yolov5 main structure is shown in Figure 1, the model consists of four parts: input side (Input), backbone network (Backbone), multi-scale feature fusion network (Neck), and detection network (YOLOHead). keywords: convolution; detection; figure; lightweight; network; odconv; structure; yolov5s cache: fcis-6350.pdf plain text: fcis-6350.txt item: #778 of 872 id: fcis-6351 author: Xu, Weilun; Wang, Yumei title: Combination Forecasting Model of R&D Intensity in Anhui Province Based on IGOWA Operator date: 2023 words: 6955 flesch: 54 summary: According to the effectiveness evaluation index system, each error index under three kinds of single prediction models and four kinds of special values of combined prediction models is calculated and normalized [17]. Predicted value and Prediction Precision of IGOWA operator combination prediction model Year Actual value of R&D intensity (%) keywords: data; error; igowa; intensity; operator; prediction; prediction model; r&d; value cache: fcis-6351.pdf plain text: fcis-6351.txt item: #779 of 872 id: fcis-6352 author: Feng, Yiqin; Wang, Yi title: Research on group distribution leakage analysis method for RSM date: 2023 words: 4241 flesch: 54 summary: SNR (Signal-To-Noise Ratio) Signal-to-noise ratio (SNR) is a common leakage analysis technique used to analyze the ratio between signal and noise in energy consumption leakage data. In order to improve the attack efficiency, researchers have proposed a large number of leakage analysis methods, which can effectively extract the intervals with significant leakage in the energy consumption curve and reduce the training parameters and data volume. keywords: analysis; attack; consumption; data; energy; leakage; method; noise; order; traces cache: fcis-6352.pdf plain text: fcis-6352.txt item: #780 of 872 id: fcis-6353 author: Yi , Nengmin; Luo, Weilin title: Research on Water Garbage Detection Algorithm Based on GFL Network date: 2023 words: 3090 flesch: 49 summary: Nengmin Yi Abstract: Aiming at the problem that existing water surface garbage detection algorithms cannot meet the tradeoff between real-time and accuracy in natural scenes, we propose a GFL (Generalized Focal Loss) based GFL_ HAM algorithm to improve the accuracy of water surface garbage detection, and better apply to water surface garbage detection application scenarios. Overall construction process of surface waste detection In order to meet the real-time and accuracy requirements of water surface garbage detection tasks, we propose a knowledge based GFL (Generalized Focal Loss) model based GFL_ HAM water surface garbage detection algorithm. keywords: accuracy; attention; detection; garbage; gfl; model; network; surface; water cache: fcis-6353.pdf plain text: fcis-6353.txt item: #781 of 872 id: fcis-6354 author: Cheng, Jixun title: Design and Implementation of Convolutional Neural Network Accelerator Based on FPGA date: 2023 words: 3584 flesch: 50 summary: GPUs have powerful parallel computing capabilities for large-scale, same-type operations [9], which are well suited for CNN operations, but their power consumption is too high ASICs, as specialized integrated circuits, can be customized with dedicated acceleration circuits for convolutional neural network models to achieve high throughput and energy efficiency 849061591@qq.com Abstract: Convolutional neural network, as a kind of feed-forward neural network, has been widely used in image recognition, speech processing and other fields in recent years. keywords: convolution; data; input; layer; module; network; pooling; size cache: fcis-6354.pdf plain text: fcis-6354.txt item: #782 of 872 id: fcis-6355 author: Zhang, Xiaodong; Su, Benlei title: Research on Beidou Navigation Interference Monitoring Technology Based on CFAR date: 2023 words: 3097 flesch: 54 summary: When ground receivers receive target signals, they also receive noise, clutter, and interference signals. How to quickly and accurately detect interference signals is a difficult problem. keywords: cfar; clutter; detection; figure; frequency; interference; navigation; signal; threshold cache: fcis-6355.pdf plain text: fcis-6355.txt item: #783 of 872 id: fcis-6362 author: Ding, Li; Ye, Shiren title: Using Bidirectional Prompt Learning in NLP Few Shot Tasks date: 2023 words: 5259 flesch: 61 summary: PET is a semi-supervised training procedure that redefines input examples as cloze-style phrases to help language models understand the given task. With the help of AutoPrompt, masked language models (MLMs) possess an innate ability to carry out sentiment analysis and natural language inference, without any additional parameters or fine-tuning. keywords: language; learning; model; processing; prompt; shot; tasks; text; training; tuning cache: fcis-6362.pdf plain text: fcis-6362.txt item: #784 of 872 id: fcis-6363 author: Li, Qingtai title: Detection of floating objects in river based on improved HRNet date: 2023 words: 2778 flesch: 51 summary: To solve the problem of river floating object detection, we proposed an improved HRNet method for river floating object detection. To solve the problem of river floating object detection, we proposed an improved HRNet[1] method for river floating object detection. keywords: detection; feature; hrnet; network; objects; rcnn; river cache: fcis-6363.pdf plain text: fcis-6363.txt item: #785 of 872 id: fcis-6365 author: Huang, Changlong; Pei, Ling; Ouyang, Qi title: Research on the Cuckoo Algorithm for Flexible Workshop Scheduling Problems date: 2023 words: 3958 flesch: 52 summary: After in-depth research, we found that the cuckoo search algorithm excels in dealing with flexible workshop scheduling problems. Therefore, future research can focus on flexible workshop scheduling problems with complex variables in the hope of obtaining better results. keywords: algorithm; cuckoo; machine; nest; problem; process; scheduling; search; time; workpiece cache: fcis-6365.pdf plain text: fcis-6365.txt item: #786 of 872 id: fcis-6366 author: Han, Zhenwei; Song, Kefei; Liu, Yang title: Research on Pulse Shaper Based on Trapezoidal Function date: 2023 words: 1919 flesch: 57 summary: The algorithm of Trapezoidal shaper In photon counting imaging system, the detector usually uses low noise charge sensitive preamplifier to realize the initial conversion of charge pulse signal. Here, the filtering processing of photoelectric pulse signal means that the pulse amplitude information of photoelectric pulse signal can be accurately presented, the accumulation of nuclear signal can be reduced, and noise interference can be eliminated as much as possible. keywords: pulse; signal; t t cache: fcis-6366.pdf plain text: fcis-6366.txt item: #787 of 872 id: fcis-6412 author: Zhou, Shuai; Hu, Xiaofeng; Zhang, Chao; Xie, Xining; Wang, Lei; Zhang, Yu title: Study on The Scattering Characteristics of Electromagnetic Wave with Dielectric Band date: 2023 words: 2768 flesch: 43 summary: The influence of different frequencies on electromagnetic wave attenuation of dielectric plates As shown in figure 6, with the increase of frequency, the attenuation of electromagnetic wave increase trend on the whole, analyze in PP board, for example, 3 MMPP plate as the frequency increases, the electromagnetic wave attenuation increases monotonously, 15 MMPP look under voltage increases monotonously with the increase of frequency electromagnetic wave attenuation, 15 MMPP plate under the negative voltage and 30 MMPP plate with increased frequency of electromagnetic wave attenuation increases after the first decreases, and the overall trend of flat. Experimental design of electromagnetic wave attenuation with dielectric plate The high voltage source is used to make the dielectric plate electrify. keywords: attenuation; conductivity; dielectric; medium; plate; power; surface; voltage; wave cache: fcis-6412.pdf plain text: fcis-6412.txt item: #788 of 872 id: fcis-6485 author: Fu, Han; Gong, Jie title: Defect detection algorithm for image reconstruction based on the self-attentive mechanism date: 2023 words: 2782 flesch: 51 summary: The current fabric defect detection method based on neural network can be divided into defect detection method based on objective detection algorithm and defect detection method based on image segmentation. [12] proposed a GAN- based framework for fabric defect detection, which first trains a GAN to explore the conditional distribution of defects in different texture backgrounds, then, the generated defects are fused to new fabric-specific locations, and finally, a deep semantic segmentation network is trained to achieve fabric defect detection by the generated defect images. keywords: cnn; defect; detection; fabric; function; image; loss; network cache: fcis-6485.pdf plain text: fcis-6485.txt item: #789 of 872 id: fcis-6908 author: Zeng, Zhuofan title: A Review of Video Action Detection Based on Deep Learning date: 2023 words: 4255 flesch: 49 summary: Keywords: Video action detection; Deep learning; Dataset. The accuracy of video action detection has been difficult to improve due to various and constantly changing video backgrounds, intrinsically complicated and changeable human action and other factors. keywords: action; computer; conference; detection; features; ieee; network; recognition; video cache: fcis-6908.pdf plain text: fcis-6908.txt item: #790 of 872 id: fcis-6909 author: Yang, Xu title: Bias-based Denoising Causal Recommendation Algorithm date: 2023 words: 4370 flesch: 51 summary: In addition, traditional recommendations and denoised causal recommendations are aggregated to obtain predictive scores. An approximation operator for backdoor adjustment is contributed, which can be easily inserted into most recommendation models. keywords: algorithm; bdcr; bias; causal; data; item; model; recommendation; user cache: fcis-6909.pdf plain text: fcis-6909.txt item: #791 of 872 id: fcis-6911 author: Fu, Guangjie; Lu, Zhiwei title: MMC circulating current suppression strategy based on improved quasi-PR control date: 2023 words: 2873 flesch: 57 summary: At present, circulation suppression strategies are mainly divided into passive circulation suppression and active circulation suppression. Circulation suppression There is a difference between the DC voltage and the sum of the upper and lower bridge arm voltage, which is fundamentally due to the unbalanced voltage equalization of the submodules, resulting in the circulation inside the MMC. keywords: circulation; controller; phase; suppression; voltage cache: fcis-6911.pdf plain text: fcis-6911.txt item: #792 of 872 id: fcis-6912 author: Qi, Xing title: Chinese Named Entity Recognition based on ERNIE date: 2023 words: 3499 flesch: 52 summary: The named entity recognition task proposed by the MUC-6 conference has been of great interest to people, and subsequently, conferences such as ACE and CoNLL-2003 have also proposed research on named entity recognition [4]. ACE not only carried out the task of named entity recognition but also included relationship recognition, reference, and anaphora resolution as part of the research [6]. keywords: entities; entity; ernie; language; learning; methods; model; recognition cache: fcis-6912.pdf plain text: fcis-6912.txt item: #793 of 872 id: fcis-6914 author: Liu, Zhongling; Luo, Yi; Liu, Chanyi title: A modified YOLOv5 helmet detection algorithm based on Swin Transformer date: 2023 words: 2399 flesch: 52 summary: Abstract: For the current stage of helmet detection in complex environments with low accuracy, missed detection and not easy to manage wearing, this paper proposes a YOLOv5 face helmet detection algorithm based on Swin Transformer improvement from the overall semantics of the image. Experiments show that the improved YOLOv5 face helmet detection algorithm mAP based on Swin Transformer improves 5.7% compared to Faster RCNN, 6.1% compared to YOLOV3, 5.3% compared to YOLOV4, and 1.6% compared to the original algorithm. keywords: accuracy; algorithm; detection; helmet; model; time; transformer; yolov5 cache: fcis-6914.pdf plain text: fcis-6914.txt item: #794 of 872 id: fcis-6916 author: Teng, Xinxin; Li, Zhenyu; Huang, Zixuan; Wu, Yiheng; Chen, Peike; Wang, Yilei title: Intelligent Switch Based on Passenger Flow Detection of Urban Rail Transit date: 2023 words: 2114 flesch: 37 summary: The application of intelligent switch device based on passenger flow detection in subway stations helps urban rail to grasp the passenger flow in time, reduces energy consumption, and effectively realizes energy saving and emission reduction while improving the efficiency and safety of intelligent management of station operation. The integration efficiency of station equipment is not high, the equipment is complex, and the buttons are jumbled. keywords: equipment; flow; operation; passenger; rail; station cache: fcis-6916.pdf plain text: fcis-6916.txt item: #795 of 872 id: fcis-6997 author: Guan, Fujun; Wang, Dewen title: Transformer fault text classification model based on double feature channel date: 2023 words: 2605 flesch: 54 summary: The characteristics of power transformer fault text are very different from the general text. Firstly, there are a large number of professional words in power transformer fault text. keywords: attention; data; fault; feature; information; model; power; text; transformer cache: fcis-6997.pdf plain text: fcis-6997.txt item: #796 of 872 id: fcis-6998 author: Zhang, Senwei; Li, Fei; Zhang, Yi title: Hierarchical federated learning with mobile edge computing in the Internet of Vehicles date: 2023 words: 3147 flesch: 53 summary: Combining the advantages of federated learning and mobile edge computing, we use a three-tier architecture of edge car network edge server cloud server federated learning, whose algorithm is HierFedProx. Combining the advantages of the two, a three-layer federated learning system of edge car network edge server cloud server is used. keywords: car; communication; computing; data; edge; learning; mobile; model; server cache: fcis-6998.pdf plain text: fcis-6998.txt item: #797 of 872 id: fcis-7082 author: Wan, Zixin title: Analysis and Prediction of Wordle Dataset Based on ARIMA and Pearson's Correlation Coefficient date: 2023 words: 3470 flesch: 60 summary: According to the rules of the game, words can only be composed of 26 English letters, so it is necessary to detect foreign words that are not composed of English letters, and this step removes the word naïve. However, for the two attributes of part of speech and word initials, the relationship between them belongs to quantitative and categorial, so we cannot use the correlation coefficient directly. keywords: correlation; data; model; number; series; test; words cache: fcis-7082.pdf plain text: fcis-7082.txt item: #798 of 872 id: fcis-7168 author: Lian, Xin; Wang, Dewen title: Insulator defect detection algorithm based on improved YOLOv5 date: 2023 words: 3347 flesch: 52 summary: Experimental results show that this method can improve the identification accuracy of insulator defect detection in transmission lines. Moreover, insulator defect detection has become the main trend of deep learning in power inspection research, which has advantages over traditional detection methods in terms of detection accuracy, speed and generalization ability of model application. keywords: algorithm; defect; detection; feature; insulator; model; module; network; power; yolov5 cache: fcis-7168.pdf plain text: fcis-7168.txt item: #799 of 872 id: fcis-7187 author: Wu, Wei title: Tea Leaf Disease Classification using Domain Adaptation Method date: 2023 words: 2788 flesch: 49 summary: The purpose of domain adaptation is to make the network model with the ability of source domain data classification be applied to predict the target domain data by reducing the difference in data distributions of the source domain and target domain. It can be seen that the average accuracy of cross-domain classification of tea leaf disease in the traditional neural network model trained only with source domain data is only 46.1%, indicating that there is a large data distribution difference between the target domain image and the source domain image after brightness processing, and the classification accuracy is low. keywords: classification; data; disease; domain; leaf; source; target; tea cache: fcis-7187.pdf plain text: fcis-7187.txt item: #800 of 872 id: fcis-7194 author: Dang, Fangbin title: Image lossless compression algorithm optimization and FPGA implementation date: 2023 words: 5113 flesch: 55 summary: And the PC side of the same picture of each group of data statistics, sorting the consumption of time range are more than 26000 ns, and even individual after the statistics of zero frequency data less, participate in sorting data more data groups, the consumption time is more than 0.01 s, that is, 10000000 ns. In addition, this grouping process makes full use of the characteristics of the local character frequencies of the data to be compressed, which can achieve better data compression results. keywords: code; coding; compression; data; figure; frequency; huffman; node; sorting; value cache: fcis-7194.pdf plain text: fcis-7194.txt item: #801 of 872 id: fcis-7234 author: Zhao, Wenqing; Chen, Haoyang title: Research on No-reference Image Quality Assessment Algorithm Based on Generative Adversarial Networks date: 2023 words: 4494 flesch: 44 summary: Image quality assessment network The IQA network consists of three main components: a feature extraction network, a metric fusion network, and a quality prediction network Keywords: Image quality assessment; Deep learning; Generative adversarial networks (GANs); Convolutional neural networks (CNNs); Feature extraction; Multi-scale feature fusion. keywords: assessment; feature; image; image quality; model; network; quality; quality assessment; reference; structure cache: fcis-7234.pdf plain text: fcis-7234.txt item: #802 of 872 id: fcis-7236 author: Cui, Jiaqi title: Intelligent robot for glass cleaning at high altitude based on rotating shaft connection and stm32 control date: 2023 words: 856 flesch: 64 summary: Frontiers in Computing and Intelligent Systems ISSN: 2832-6024 | Vol. 3, No. 2, 2023 64 Intelligent robot for glass cleaning at high altitude based on rotating shaft connection and stm32 control Jiaqi Cui* School of Electrical and Control Engineering of North China University of Technology, Beijing, China * Corresponding author Email: Keywords: High altitude; Operation quadcopter; Deep learning; Rotary shaft vehicle. keywords: cleaning; control; glass cache: fcis-7236.pdf plain text: fcis-7236.txt item: #803 of 872 id: fcis-7512 author: Zhou, Bainan; Li, Xu title: Multimodal Emotion Analysis Model based on Interactive Attention Mechanism date: 2023 words: 5025 flesch: 54 summary: For multi-modal data representation, neural networks are usually used to represent data of different modes respectively. SELF-MM [15]: Multi-modal sentiment analysis task is realized by using multi-task learning and single-modal label automatic generation. keywords: analysis; attention; data; mechanism; modal; mode; multi; multimodal; representation; sentiment; task cache: fcis-7512.pdf plain text: fcis-7512.txt item: #804 of 872 id: fcis-7514 author: Chen, Fankai; Liu, Qinyu; Cong, Xiaohan; Dong, Xiuhuan; Zhang, Yuanyuan title: Three-dimensional path planning of UAV in complex urban environment date: 2023 words: 2883 flesch: 58 summary: Path planning integrates the cost of navigation by improving navigation cost function, increasing route planning, reducing path planning, increasing route security constraints, and adjusting the weight of adaptive cost functions. The core of UAV path planning technology is path planning algorithm. keywords: algorithm; cost; flight; node; path; planning; search; uav cache: fcis-7514.pdf plain text: fcis-7514.txt item: #805 of 872 id: fcis-7516 author: Zhang, Tingan title: Kerberos authentication protocol implementation based on DHR atypical construct date: 2023 words: 4446 flesch: 40 summary: Through detailed analysis and experimental verification of the scheme, we demonstrate that the scheme can improve the performance and reliability of the system while ensuring authentication security. (3) Others In addition to the above two relatively effective attacks against Kerberos, Kerberos authentication systems have the same security issues as other security systems: key storage issues, system program security issues, and so on. 2.3. keywords: authentication; kerberos; kerberos authentication; key; process; scheme; security; user cache: fcis-7516.pdf plain text: fcis-7516.txt item: #806 of 872 id: fcis-7518 author: Chen, Fei; Guan, Dichen title: Application of Ecological Planting and Breeding Mode in Guangxi based on Internet Plus date: 2023 words: 2362 flesch: 33 summary: Problems of ecological breeding model in Mashan County Although the ecological breeding model in Mashan County 86 has achieved some results, there are still some deficiencies, which need to be further improved and perfected. Key points of ecological chicken breeding and management technology keywords: breeding; chicken; farming; internet; model; planting cache: fcis-7518.pdf plain text: fcis-7518.txt item: #807 of 872 id: fcis-7521 author: Zhan, Shiquan; Chen, Jiajun; Li, Chengxuan title: Let Starry Light the World date: 2023 words: 3265 flesch: 56 summary: Therefore, we initially use this basic model to analyze the influence of different light pollution factors. The results showed that the scheme using lampshades worked best in suburban and urban communities, reducing light pollution risk levels by about 52 percent. keywords: factors; figure; intervention; level; light; model; pollution; risk cache: fcis-7521.pdf plain text: fcis-7521.txt item: #808 of 872 id: fcis-7522 author: Sun, Lanlan title: An Overview of Intelligent Parking Systems date: 2023 words: 2341 flesch: 48 summary: Gather parking point data into a data center to comb and comprehensive data application provide parking operators scheduling management, financial management, operation analysis, marketing management, advertising management and parking service for owners to provide parking query parking reservation, parking path navigation, electronic payment, monthly, bill inquiry, convenient parking services. Abstract: With the development of Internet technology, intelligent parking system has been developed. keywords: information; internet; lot; parking; system; technology; things cache: fcis-7522.pdf plain text: fcis-7522.txt item: #809 of 872 id: fcis-7523 author: Fan, Linda title: Experimental research and numerical simulation based on granary effect date: 2023 words: 2116 flesch: 54 summary: In the formula, �⃗�𝑗 、 �⃗�𝑗 、𝑧𝑗 are the coordinates of particulate matter j in the rectangular coordinate system; �⃗�𝑥 、 �⃗�𝑦 、�⃗�𝑧 are the velocities of particulate matter j in the X, Y and Z directions in the rectangular coordinate system. In the formula: k is the number of particles colliding with particle j; 𝑓𝑛，𝑖𝑗 is the normal force between particle i and particle j; 𝑓𝑡，𝑖𝑗 is the tangential force between particle i and particle j. The normal force on the particles is: 𝑓𝑛，𝑖𝑗 = 𝑓𝑐𝑛，𝑖𝑗 + 𝑓𝑑𝑛，𝑖𝑗 (2) 𝑓𝑐𝑛，𝑖𝑗 keywords: effect; particle; silo; ⃗ �; � ⃗ cache: fcis-7523.pdf plain text: fcis-7523.txt item: #810 of 872 id: fcis-7524 author: Yang, Xin title: Quantum fuzzy neural network based on fuzzy number date: 2023 words: 5308 flesch: 60 summary: Framework of quantum fuzzy neural network model based on fuzzy number in the training process In the training process, the data pre-processing unit extracts features from the huge data, retains the valuable parameters, reduces the model computation and improves the computing efficiency. U ( )        − −= +  (15) 3.5. keywords: data; fuzzy; model; network; number; quantum;   cache: fcis-7524.pdf plain text: fcis-7524.txt item: #811 of 872 id: fcis-7525 author: Wang, Yuan; Yang, Zhoumeng; Zhang, Xiyan title: Improving NLP Accuracy with Stack-Propagation and Knowledge Distillation: A Joint Model for Intent Detection and Slot Filling date: 2023 words: 3220 flesch: 51 summary: To address the issue of error propagation caused by pipelined approaches, researchers have proposed joint models in recent times. Recently, there has been a growing interest in joint models to address the issue of error propagation caused by pipelined approaches in slot-filling and intent detection tasks. keywords: detection; filling; information; intent; model; slot; tasks cache: fcis-7525.pdf plain text: fcis-7525.txt item: #812 of 872 id: fcis-7558 author: Zhou, Yang title: Divide-and-Conquer Template Attack on Scloud date: 2023 words: 2380 flesch: 49 summary: Keywords: Post quantum cryptography; Side-channel attack; Template attack; Convolutional neural networks. In the context of template attacks, the role of Convolutional Neural Networks (CNN) is primarily as a classifier. keywords: attack; information; key; quantum; scloud; template cache: fcis-7558.pdf plain text: fcis-7558.txt item: #813 of 872 id: fcis-7570 author: Wang, Shuaina; Yin, Hang; Wang, Xiangkun title: Patient-oriented online healthcare services platform: development based on Vue3 and Ts date: 2023 words: 3742 flesch: 59 summary: Keywords: Online healthcare platform; Vue.js; Typescript; Pinia; SignalR. 1. Database Analysis In this project, we use SQL Server as the database management system, and access and manipulate data through Entity Framework Core, a powerful, secure and stable relational database management system that can meet the data storage and management needs of online healthcare platforms. keywords: code; doctor; drug; healthcare; online; page; platform; request; user; vue cache: fcis-7570.pdf plain text: fcis-7570.txt item: #814 of 872 id: fcis-7575 author: Tang, Yuxuan title: Deep learning in drug discovery: applications and limitations date: 2023 words: 5283 flesch: 49 summary: To address these challenges, future research efforts should focus on developing new methods for data generation and curation to improve the quality of training data, as well as developing new deep learning models that are less susceptible to overfitting and more interpretable. However, there are also several limitations and challenges associated with the use of deep learning in drug discovery, including the lack of high- quality training data, overfitting and generalization issues, interpretability and explainability of deep learning models, and legal and ethical considerations. keywords: challenges; data; design; discovery; drug; drug discovery; learning; models; molecules cache: fcis-7575.pdf plain text: fcis-7575.txt item: #815 of 872 id: fcis-7576 author: Sun, Hao; Chen, Li title: Design of application layer software platform of remote monitoring system date: 2023 words: 1513 flesch: 60 summary: Software interface Login interface, homepage, data management interface, device management interface, menu management interface, role management and user management can work successfully. Front-end design diagram As shown in Figure 3, the front-end software is divided into seven pages, which are login interface, home page (workbench), data management interface, device management interface, menu management interface, role management interface and user management interface. keywords: data; end; interface; software cache: fcis-7576.pdf plain text: fcis-7576.txt item: #816 of 872 id: fcis-7595 author: Wang, Xiaolong title: Procedural Modeling Method of Pipe Network Based on Spline Grammar date: 2023 words: 4012 flesch: 56 summary: Example of pipe model When users need other types of pipe bodies, they can manually switch the spline type of pipe body objects in the editor mode. At the same time, after removing the spline terminator in the grammar structure, the remaining terminators adaptively calculate their pending parameters (such as intermediate filling node coordinates and compact coefficients) according to the generation of spline terminators and generate pipe fiettors, and finally complete the splicing of pipe body and pipe fittings. keywords: body; grammar; head; method; modeling; pipe; point; shape; spline cache: fcis-7595.pdf plain text: fcis-7595.txt item: #817 of 872 id: fcis-7689 author: Zhao, Shangyu; Lin, Ping title: A Distributed Streaming Computing Model Management System date: 2023 words: 1854 flesch: 53 summary: In this paper, we propose a management method for streaming computing models, which enables hot loading of computing models by means of custom classloader, and design a distributed management mechanism that can manage computing models in a distributed system, and computing models can be synchronized up and down in each computing node in the distributed system. This makes it easier to manage computational models in a streaming computing cluster. keywords: computing; model; streaming; system cache: fcis-7689.pdf plain text: fcis-7689.txt item: #818 of 872 id: fcis-7690 author: Liao, Weichen title: Research on Detection Algorithm of Safety helmet based on improved YOLOX date: 2023 words: 2015 flesch: 55 summary: In this paper, SE module is inserted into neck network of detection network and connected with output of dark3, dark4 and dark5 in CSPDarknet53 feature extraction network. The decoupling detection Head network independently designed by YOLOX is used in the head part, which introduces the idea of Anchor-free [9] target detection and adopts the point set prediction method for target detection, which avoids the uncertainty of Anchor selection in Anchor- based method and can locate small targets more accurately. keywords: algorithm; detection; helmet; loss; module; network; yolox cache: fcis-7690.pdf plain text: fcis-7690.txt item: #819 of 872 id: fcis-7692 author: Gao, Yuan title: The Problems of “Artificial Intelligence” in Modern Philosophy and Science date: 2023 words: 8391 flesch: 51 summary: Machine learning models can be thought of as increasingly complex mathematical forms. However, as machine learning models become more complex and general-purpose, such as deep neural networks, the mathematical type chosen appears to become less and less scientifically important. keywords: data; education; humans; intelligence; learning; logic; machine; machine learning; new; philosophy; problem; program; science; systems cache: fcis-7692.pdf plain text: fcis-7692.txt item: #820 of 872 id: fcis-7702 author: Liu, Yue; Luo, Li; Hong, Weibin title: Research on Video Synopsis Based on Deep Learning Target Detection and Target Trajectory Optimization date: 2023 words: 4030 flesch: 52 summary: Reasonably place the targets in the new condensed video sequence, determine the index of all targets in the new condensed video stream, and finally integrate each frame of target images into the background image according to the set index rules, ultimately obtaining the synopsis video. 4) Repeat steps (2) - (3) until the confirmed trajectory or video frame ends. keywords: algorithm; detection; frame; image; method; results; target; technology; tracking; trajectory; video cache: fcis-7702.pdf plain text: fcis-7702.txt item: #821 of 872 id: fcis-7982 author: Li, Wenli; Wu, Gang title: One-shot Based Knowledge Graph Embedded Neural Architecture Search Algorithm date: 2023 words: 2956 flesch: 47 summary: An existing approach is to divide the search space into macro search space and micro search space. Researchers usually introduce neural network architecture search into knowledge graph embedding for machine automatic construction of appropriate neural networks for each dataset. keywords: algorithm; architecture; evaluation; graph; knowledge; search; space cache: fcis-7982.pdf plain text: fcis-7982.txt item: #822 of 872 id: fcis-7983 author: Tan, Xiaoqin title: Named Entity Recognition of Electronic Medical Records Based on Multi-Feature Fusion date: 2023 words: 3481 flesch: 48 summary: The paper studies the problem of named entity recognition in Chinese electronic medical records, and proposes a method based on the Bert-Bi-LSTM- CRF model. The proposed method can not only effectively solve the problem of named entity recognition in Chinese electronic medical records but also achieve better results in practical applications, and has certain promotional and application value. keywords: bert; chinese; entity; information; lstm; model; recognition cache: fcis-7983.pdf plain text: fcis-7983.txt item: #823 of 872 id: fcis-7984 author: Dong, Bo title: A Systematic Review of the Enterprise Digital Transformation Literature and Future Outlook date: 2023 words: 3173 flesch: 19 summary: bo.dong.mnl@eac.edu.ph Abstract: This paper aims to explore the impact of digital transformation on enterprises and society, focusing on the main research directions, research achievements, best practices, and future research directions. Digital transformation profoundly affects enterprises and society by enabling innovation, enhancing competitiveness, promoting efficiency, and facilitating economic growth opportunities. keywords: data; enterprises; future; research; transformation; vol cache: fcis-7984.pdf plain text: fcis-7984.txt item: #824 of 872 id: fcis-7986 author: Liu, Fuqiuxuan; Li, Chongqing title: Application of VMD feature fusion in fault diagnosis of rolling bearings date: 2023 words: 1328 flesch: 58 summary: Conclusion The VMD feature fusion method proposed in this article can effectively diagnose rolling bearing fault signals under different working conditions, and the diagnostic accuracy is better than the EEMD method. Accurately detecting bearing faults and implementing necessary maintenance measures based on their types is of great significance for ensuring enterprise safety production and reducing economic losses [2]. keywords: bearing; fault cache: fcis-7986.pdf plain text: fcis-7986.txt item: #825 of 872 id: fcis-7987 author: Gan, Gang; Kong, Weiju title: Research on Network Intrusion Detection Based on Transformer date: 2023 words: 3140 flesch: 50 summary: Deep learning algorithms can establish complex mapping relationships between network data, and can extract hidden correlation features between data features to achieve data recognition and prediction. TBL intrusion detection model 2.2. keywords: attack; data; dataset; detection; intrusion; model; network; samples cache: fcis-7987.pdf plain text: fcis-7987.txt item: #826 of 872 id: fcis-7988 author: Luo, Ruxue title: Research on logistics Route Optimization based on AFSA date: 2023 words: 1582 flesch: 54 summary: In this study, from the perspective of logistics cost, AFSA was improved to explore the realization of logistics path planning optimization of electroplating products. Jiang Ming et al. proposed a two- population evolutionary strategy of improved genetic algorithm based on fixed length binary path coding to achieve global path optimization. keywords: algorithm; fish; logistics; path; planning; swarm cache: fcis-7988.pdf plain text: fcis-7988.txt item: #827 of 872 id: fcis-7989 author: Jiang, Yinling; Zhu, Ke; Zhang, Qiang; Zhao, Shuai title: Stick slip vibration control of drill string based on torque feedforward and sliding mode controller date: 2023 words: 2848 flesch: 66 summary: Among them, the TF-SMC-PID controller has significantly better overshoot indicators for drill bit speed, and the peak to peak oscillation is significantly lower compared to other controllers. 0 10 20 30 0 3 6 9 12 15 w / r ad -s t / s wref wr TF-SMC-PID wr TF-SMC wr SMC wr PID (a) 0 10 20 30 0 4 8 12 16 20 w / r ad -s t / s wref wr TF-SMC-PID wr TF-SMC wr SMC wr PID (b) Compared to PID controllers, TF-SMC-PID controllers significantly increase the response speed of drill bit speed, shorten the adjustment time, significantly reduce overshoot, and significantly lower the peak value of vibration when controlling the drill string system. keywords: controller; drill; speed; string cache: fcis-7989.pdf plain text: fcis-7989.txt item: #828 of 872 id: fcis-7990 author: Wen, Peining; Liu, Yilin; Liu, Tong; Zhou, Liqiang; Cheng, Qinyan title: Path tracking of Mr Fluid braking System based on PID control date: 2023 words: 2047 flesch: 60 summary: In order to simplify the calculation of braking torque, our team makes the following assumptions about Mr Fluid brake: (1) The velocity of Mr Fluid is only related to the radius. Frontiers in Computing and Intelligent Systems ISSN: 2832-6024 | Vol. 3, No. 3, 2023 34 Path tracking of Mr Fluid braking System based on PID control Peining Wen1, Yilin Liu2, Tong Liu2, Liqiang Zhou2, Qinyan Cheng2 1 College of Automation Central South University, Changsha, Hunan 410083, China 2 The College of electrical and mechanical engineering, Central South University, Changsha Hunan 410083, keywords: braking; fluid; path cache: fcis-7990.pdf plain text: fcis-7990.txt item: #829 of 872 id: fcis-7991 author: Liu, Yulin title: Quantum-based Detection of Higly Semantically Similar Social bot date: 2023 words: 3823 flesch: 58 summary: Experiments show that the method we designed can accurately identify social bot, and the cross- disciplinary combination the quantum similarity algorithm has better performance than the traditional similarity algorithm in judging the similarity of social bot texts. Processing and classification, and then adding the quantum similarity algorithm in the emerging quantum discipline in recent years to the structural system of social bot detection to perform similarity clustering, which greatly improves the operating efficiency of the system, and then obtains the corresponding user attribute characteristics for artificial intelligence. keywords: bot; detection; learning; number; quantum; similarity; users; value cache: fcis-7991.pdf plain text: fcis-7991.txt item: #830 of 872 id: fcis-8564 author: Li, Xiaomeng; Su, Xing title: Influence of Spatial Perception Ability on Virtual Annotation Response in Teleoperation of Excavator date: 2023 words: 6205 flesch: 46 summary: Although the Rnun index has nothing to do with the strength of spatial perception ability in this experiment, due to the lack of relevant studies, in order to ensure the accuracy of the conclusions, experiments can be added in the future, the difficulty and type of VA operations can be increased in the experiment, or the obstacles that may be encountered in 49 the actual work scene can be represented in a variety of different VA forms, so as to re-explore the relationship between spatial perception ability and response accuracy in various situations, and then support the design of VA in remote operating systems. Correlation between SPA and its sub-items Test items SPA SV SR SPA Pearson correlation coefficient 1 0.473** 0.745** Sig. keywords: ability; correlation; items; perception; response; spa; table; teleoperation cache: fcis-8564.pdf plain text: fcis-8564.txt item: #831 of 872 id: fcis-8565 author: Liu, Shumin; Chen, Jia; Sun, Jinpeng title: Glucose Electrocatalysis of Multi-walled Carbon Nanotubes/Polyvinyl Alcohol Conducting Hydrogel Composite Platinum Electrode date: 2023 words: 3339 flesch: 38 summary: Testing Synergistic effect of MWCNTs/PVA conductive hydrogel electrode film and platinum electrode: 0.10mol /L HClO4, 0.10mol /LNaOH and 0.1mol /L For comparison, a carbon tube modified platinum electrode and a platinum electrode are also displayed. keywords: electrode; figure; film; glucose; hydrogel; mwcnts; platinum; platinum electrode; pva cache: fcis-8565.pdf plain text: fcis-8565.txt item: #832 of 872 id: fcis-8574 author: Tian, Hui; Liu, Gang title: Target Local Matching Recognition Algorithm based on Improved Harris Key Point Detection Operator date: 2023 words: 1819 flesch: 48 summary: Matching results 2 From the detection results of Figure2, it can be seen that the feature points extracted by the original Harris algorithm have a pair of matching errors, and the points on the wing are matched to the fuselage; The improved Harris algorithm extracts feature point pairs that match correctly, and for unblocked aircraft, the improved algorithm extracts feature points on the nose, tail, and wing, while the original algorithm does not extract feature points on the wing. Therefore, on the basis of Harris corner point detection, the corner point detector is constructed by calculating the minimum eigenvalue of the autocorrelation matrix as the corner point response function, so that there is no need to adjust the k value: ),min( 21 R (6) 3. keywords: algorithm; corner; harris; point; target cache: fcis-8574.pdf plain text: fcis-8574.txt item: #833 of 872 id: fcis-8575 author: Liu, Shumin; Chen, Jia; Sun, Jinpeng title: Preparation and Characterization of Conductive Hydrogel Electrode Films of Nano Platinum/Multi-Walled Carbon Nanotubes/Polyvinyl Alcohol date: 2023 words: 2576 flesch: 43 summary: As shown in Figure 3 (A), when the electrode potential was 0.5V, the current time curve of PtNPs/MWCNTs/PVA conducting hydrogel electrode film against glucose assessed the stability of the electrode film. As shown in Figure 1 (C), PtNPs electrode film has a weak electrocatalytic activity on glucose. keywords: electrode; film; glucose; hydrogel; mwcnts; ptnps; pva; solution cache: fcis-8575.pdf plain text: fcis-8575.txt item: #834 of 872 id: fcis-8577 author: Yan, Xian title: Key Factors Influencing Network Resilience in Dynamical Networks date: 2023 words: 2790 flesch: 55 summary: So how to improve network resilience and thus avoid network failures is a hot topic. These strategies can help dynamic networks enhance network resilience, which is an important criterion for reducing network failures in real-world systems. keywords: failure; key; network; nodes; recovery; resilience cache: fcis-8577.pdf plain text: fcis-8577.txt item: #835 of 872 id: fcis-8578 author: Zeng, Jingxiao title: Diagnostic Study of MBR Membrane Fouling based on CA-ResNet18 date: 2023 words: 3996 flesch: 48 summary: Comparison of average accuracy Diagnostic models Average accuracy rate CA-CNN 61.63% ResNet18 91.58% SE-ResNet18 93.10% SKNet-ResNet18 96.10% CA-ResNet18 99.25% To evaluate the diagnostic accuracy of the proposed CA- ResNet18 model in membrane fouling fault diagnosis, a comparison experiment was conducted using the membrane fouling fault dataset. Thus, it is proved that the CA-ResNet18 proposed in this paper applies to the field of membrane fouling fault diagnosis. keywords: attention; diagnosis; fault; feature; fouling; layer; mechanism; membrane; model; network; neural; resnet18 cache: fcis-8578.pdf plain text: fcis-8578.txt item: #836 of 872 id: fcis-8579 author: Liu, Yajing title: Smart Medical System based on 5G and IoT Technology date: 2023 words: 2732 flesch: 41 summary: In addition, the efficient data transmission capability of the IoT transmission layer should be able to transmit a large amount of smart medical data at high speed to meet the needs of smart medical care. In recent years, scientists and technologists have continued to come up with new modes of thinking, and rapidly developing technologies have led to huge breakthroughs in medical technology. keywords: data; healthcare; iot; medical; services; technology cache: fcis-8579.pdf plain text: fcis-8579.txt item: #837 of 872 id: fcis-8580 author: Li, Changhong title: Multi-objective Optimization Overlapping Community Detection Algorithm based on Subgraph Structure date: 2023 words: 2416 flesch: 49 summary: The main methods of overlapping community detection include algorithm based on factional filtering, algorithm based on local extension, algorithm based on edge partition, algorithm based on fuzzy detection, algorithm based on k-clique seepage, overlapping community detection algorithm based on local expansion and optimization, and overlapping community detection algorithm based on multi-objective optimization. Network community structure detection, also known as network clustering, is a technology to reveal the community structure formed by network aggregation. keywords: algorithm; clique; community; core; detection; network; nodes cache: fcis-8580.pdf plain text: fcis-8580.txt item: #838 of 872 id: fcis-8581 author: Liu, Ziyun; Ren, Feiyu title: Algorithm Improvement of Movie Recommendation System based on Hybrid Recommendation Algorithm date: 2023 words: 4430 flesch: 43 summary: In calculating user similarity, the Euclidean distance [4] is a more intuitive similarity algorithm. The SVD technique is used to complement the user-item rating matrix to predict user ratings of items, which requires us to find a complementary method that minimizes the perturbation of the original matrix. keywords: algorithm; item; matrix; recommendation; recommendation algorithm; similarity; users; value cache: fcis-8581.pdf plain text: fcis-8581.txt item: #839 of 872 id: fcis-8582 author: Ge, Li; Zhou, Maojun title: Improvement of the Method of Comparing Coefficients Based on Constant Coefficients Non-Homogeneous Linear Differential Equations date: 2023 words: 3664 flesch: 65 summary: Let 2( )R x dx ,according to Theorem 1, ( )R x satisfies the differential equation ( ) 1R x  ,and we can obtain 2 1d  , 1 2 d  is solved, then * 2 2 2 1 2 xy x e , the general solution of the original equation is 2 2 2 2 2 1 2 1 1 3 1 4 2 8 2 x x xy C e C xe x x x e      ( 1 2,C C are any constants) ( ) ( )x i x p x i x q x i x u x iv x             After simplification, it is necessary to [ ( ) ( ) ( )] keywords: equation cache: fcis-8582.pdf plain text: fcis-8582.txt item: #840 of 872 id: fcis-8583 author: Xu, Jiacan; Hu, Binbin; Yang, Mingye; Xing, Shiyu; Zhou, Peng title: Feature Extraction Algorithm of Cutter Head Pressure Signal based on Stack Auto-encoder date: 2023 words: 1964 flesch: 51 summary: TBM mainly includes tool system, cutter head system, hydraulic propulsion system, etc., and the tool system as the core component of the full section rock tunnel boring machine, its performance and reliability directly affect the engineering efficiency and construction cost. In addition, Jin et al.[6] investigated the influence of rock properties and changes in TBM parameters on hob failure. keywords: cutter; failure; head; hob; rock; system; tbm; tool cache: fcis-8583.pdf plain text: fcis-8583.txt item: #841 of 872 id: fcis-8584 author: Zheng, Bowen title: Exploration and Improvement of Modernization of Municipal Governance Driven by Digital Reform date: 2023 words: 3576 flesch: 32 summary: The construction of municipal governance modernization, the lack of data governance means, digital reform application is not much. Strengthen the Training and Introduction of Digital Talents in Municipal Governance To construct the modernization of municipal governance, we must strengthen the training and introduction of digital talents, and improve the level of urban digital governance and management. keywords: application; construction; data; digital; governance; government; modernization; reform; security cache: fcis-8584.pdf plain text: fcis-8584.txt item: #842 of 872 id: fcis-9405 author: Ma, Zhikuan; Wang, Guangsheng; Song, Yuheng; Yu, Tong; Lei, Zhiyi title: Domestic and Foreign Trade Container Generation Measurement Based on GCM & RM Model: -- The Example of West African Countries date: 2023 words: 6038 flesch: 47 summary: Generally speaking, the larger the scale of foreign trade, regional foreign trade container generation (Q) is also the larger; the faster the speed of regional development, the faster the growth of foreign trade container generation, therefore, accurate evaluation and prediction of foreign trade scale and foreign trade development speed is an important basis for predicting foreign trade container generation. 375421.2 457772.7 896210.7 1139222.7 929082 Equatorial Guinea (GQ) 10418.1 30261 126703.5 81427.5 39824.4 Republic of the Congo (CG) 11386.38 32657.63 99349.25 144819.675 117091.98 Angola (AO) 81928 225113.35 449175.65 557676.35 257183.85 Gabon (GA) 18433.8 31392.9 72210.6 73250.1 61838.7 Democratic Republic of the Congo (CD) 50415.75 77673.75 232241.63 305353.125 342601.88 Namibia (NA) 30261 53615.1 120697.5 146708.1 94040.1 South Africa (ZA) 943346.3 1960219.8 2895631.2 2948056.65 2345978.3 Based on this data set, which spans a period of 20 years, future forecasts of foreign trade container volumes for the 29 countries in the delimited region can be made later on. (2) Calculated statistics on domestic freight generation for West African countries After obtaining the relationship between domestic freight generation and GDP, population, road length and railway length using the multiple linear regression analogy method, the GDP, population, railway length and road length of West African countries from 2000 to 2020 can be found and then substituted into the formula to find the domestic freight generation of West African countries. keywords: container; container generation; countries; development; generation; goods; regression; trade; trade container; volume cache: fcis-9405.pdf plain text: fcis-9405.txt item: #843 of 872 id: fcis-9406 author: Wang, Jinyu; Wu, Peiyu title: An Improved Three-point Method for Power Flow Calculation based on Halton Sequence date: 2023 words: 5426 flesch: 56 summary: At present, various improved versions of point estimation methods have been developed, such as probabilistic power flow developed by point estimation method in literature The new energy power generation presents intermittenity and volatility, so it is a hot research topic to use the theory of point estimation method to study the power system planning based on uncertainty quantity. keywords: calculation; distribution; estimation; estimation method; flow; formula; method; point; power; wind cache: fcis-9406.pdf plain text: fcis-9406.txt item: #844 of 872 id: fcis-9409 author: Wang, Yian title: An Underwater Target Ranging System based on Binocular Vision date: 2023 words: 4040 flesch: 51 summary: Calibration parameters of underwater binocular camera Parameter Left camera Underwater Distance Measurement Experiment The images of underwater objects are obtained by binocular underwater camera, and the improved CLAHE algorithm is used to process the images. keywords: calibration; camera; distance; distortion; figure; image; measurement; system; target; underwater cache: fcis-9409.pdf plain text: fcis-9409.txt item: #845 of 872 id: fcis-9418 author: Rao, Han title: Ethical and Legal Considerations behind the Prevalence of ChatGPT: Risks and Regulations date: 2023 words: 5876 flesch: 27 summary: First, enterprises and scientific institutions should make perfect internal management systems such as technical norms, ethical norms, and safety norms of artificial intelligence development and application in accordance with the law, and set special internal supervision departments to supervise the whole process of technology development and application; second, in the process of artificial intelligence technology development, enterprises and scientific institutions should use technical means and strengthen management, obtain data through legal channels, ensure data storage security, process data in compliance with laws and regulations, and avoid ethical risks such as algorithm discrimination; furthermore, enterprises and scientific institutions should actively fulfill their social responsibility disclosure mechanisms, open information on data sources, storage and processing, and actively disclose possible negative impacts on society, users and other relevant stakeholders in the process of development and application of artificial intelligence technology, and accept public supervision. Under the market economy system, enterprises, especially Internet technology giant companies, should become the main body of artificial intelligence technology development and industrialization, follow policy guidance, take full advantage of government policies and financial support, step up investments in R&D of fundamental hardware and core technologies, and accelerate the deployment of relevant industries, promote the transformation of technological achievements and commercial applications, form good cycle of economic benefits and scientific and technological research and development, continuously narrow the technological gap with the world's leading companies, and master independent, controllable and advanced artificial intelligence technologies. keywords: algorithm; chatgpt; contents; data; development; human; information; intelligence; law; risks; social; technology; users cache: fcis-9418.pdf plain text: fcis-9418.txt item: #846 of 872 id: fcis-9419 author: Fu, Yu; He, Qinghui title: Horizontal Gas Well Liquid Accumulation State Determination based on Ensemble Learning Algorithm date: 2023 words: 2108 flesch: 42 summary: Research progress on critical liquid carryover and liquid accumulation models for water-producing gas wells[J]. Currently, the models used to calculate the critical liquid-carrying flow rate in gas wells include the Turner droplet model, Coleman model, liquid film model for vertical wells; the Belfoid model, Li Yingchuan impact oscillation model, Shekhar model for inclined wells; and the stratified flow model, K-H wave model, and Wang model for horizontal wells. keywords: accumulation; gas; liquid; model; prediction; wells cache: fcis-9419.pdf plain text: fcis-9419.txt item: #847 of 872 id: fcis-9420 author: Wang, Jinyu; Shi, Haolin title: Research on Voltage Sag Detection Algorithm based on Regional Transmission System date: 2023 words: 4646 flesch: 65 summary: Voltage U at α axis and the projection of the β axis represents the voltage at the instantaneous components in the αβ coordinate system are ud=Ucosφ and uq=Usinφ. China Abstract: Voltage sag is the most common power quality issue and often brings huge economic losses. keywords: method; phase; sag; sin; system; transformation; u t; u u; value; voltage; voltage sag cache: fcis-9420.pdf plain text: fcis-9420.txt item: #848 of 872 id: fcis-9421 author: Ming, Xiaoke; Jiang, Shaodong; Duan, Yue title: Global Path Planning Method for Parks based on Complete Coverage Cleaning Task date: 2023 words: 4979 flesch: 43 summary: U-shaped turning diagram In this paper, an improved bow-shaped coverage algorithm is proposed to generate coverage paths under the constraint of minimum turning radius to improve the coverage of turnaround areas. Complete coverage path planning is different from point to point path planning, the final result is to plan a continuous path that starts from the starting position and traverses the whole operation area to the end position, and the path evaluation index is usually the area coverage. keywords: area; coverage; figure; lane; lane area; map; path; platform; raster; sanitation cache: fcis-9421.pdf plain text: fcis-9421.txt item: #849 of 872 id: fcis-9422 author: Xie, Weiting title: Entity Linking based on RoFormer-Sim for Chinese Short Texts date: 2023 words: 4122 flesch: 52 summary: Experimental Dataset This article uses the dataset provided by the CCKS2020 (the 2020 National Knowledge Graph and Semantic Computing Conference) short text entity linking evaluation. 4. Conclusion This paper aims to construct an entity linking model based on the RoFormer-Sim pre-training model for Chinese short texts and verifies it on the dataset provided by the CCKS2020 (National Knowledge Graph and Semantic Computing Conference 2020) short text entity linking evaluation. keywords: candidate; entities; entity; knowledge; linking; model; roformer; sim; text; training cache: fcis-9422.pdf plain text: fcis-9422.txt item: #850 of 872 id: fcis-9423 author: Shao, Keyong; Pan, Yuda title: Design of Preset Performance Reverse Step Attitude Controller for Four-rotor UAV date: 2023 words: 4200 flesch: 62 summary: Keywords: UAV Attitude Angle Control; Extended State Observer; Preset Performance Control; Backstepping Control. For equation (25), where, 1X̂ , 2X̂ and 3X̂ respectively represent four the estimated value of attitude Angle, attitude Angle rate and lumped interference of the rotor UAV 3I are represented by the unit matrix 3 3 , where 0 represents the zero matrix of appropriate dimension, H is the observer gain matrix, w is the bandwidth of the linear expanded state observer and satisfies 0w  . keywords: angle; attitude; control; performance; system; t t; uav cache: fcis-9423.pdf plain text: fcis-9423.txt item: #851 of 872 id: fcis-9424 author: Chao, Ziheng title: Automatic Play based on LR and SVM Algorithms: -- Take Chrome Dion Game as an Example date: 2023 words: 3147 flesch: 51 summary: In fact, automatic game play is the basis for training AI game AI, 2019 OpenAI through reinforcement learning methods to train a set of team-based hide-and-seek game AI, they are red seekers and blue hiders, the game environment is scattered with some objects, both sides can grab and lock in place, used to stop each other's line, in many experiments appeared a surprising effects, not only showing superb dexterity to collar tools for dodging or blocking, the AI even learned to work in teams [3]. First of all, for developers, it can assist game development, reduce game production costs, make game development convenient, produce higher quality games in a shorter time, reduce the workload of developers, and make the game realistic in the player's game experience, improve playability and fun. keywords: algorithm; data; function; game; intelligence; kernel; regression cache: fcis-9424.pdf plain text: fcis-9424.txt item: #852 of 872 id: fcis-9451 author: Liao, Zhen; Lin, Guojun title: Research on Sketching Face Headshot Generation based on Improved CycleGAN date: 2023 words: 2468 flesch: 62 summary: The conversion process of the image from X domain image to Y domain image is explained as an example. The generator G represents the mapping of X-domain image to Y- domain image, and the generator F represents the mapping of Y-domain image to X-domain image. keywords: avatars; domain; image; loss; model; sketch cache: fcis-9451.pdf plain text: fcis-9451.txt item: #853 of 872 id: fcis-9453 author: Zhu, Zhiren; Zhou, Liming; Chen, Fankai; Liu, Chen; Meng, Fanrun title: Improved YOLOv5l-based Detection of Surface Defects in Hot Rolled Steel Strips date: 2023 words: 3457 flesch: 55 summary: Characterization of surface defect detection by a novel pulsed leakage magnetic detection method. Surface defect detection of strip steel based on improved YOLOv3 algorithm. keywords: accuracy; algorithm; defects; detection; model; module; network; strip; surface; target; yolov5l cache: fcis-9453.pdf plain text: fcis-9453.txt item: #854 of 872 id: fcis-9454 author: Chen, Sijia; Tang, Sihan title: Computer Aided Design of Protective Gear and the Mathematical Statistics for Mechanical Mechanism from Falls date: 2023 words: 2721 flesch: 56 summary: However, although head injuries in the elderly are not the most common type of injury, they are quite harmful to the elderly. Therefore, head injuries caused by falls in the elderly should arouse the attention of all sectors of society. keywords: elderly; fall; head; injuries; injury; population cache: fcis-9454.pdf plain text: fcis-9454.txt item: #855 of 872 id: fcis-9459 author: Wang, Tie; Yang, Jing; Wang, Junlei; Zhang, Fan title: Intelligent Calculation of Automobile Brand Power Score based on Analytic Hierarchy Process and Entropy Weight Method date: 2023 words: 4500 flesch: 51 summary: Abstract: In order to improve the brand power of national auto brands and build a strong country for national auto brands, based on the research of this paper, the use of analytic hierarchy process and entropy weight method is used to calculate the score of auto brand power. Then, the AHP + entropy weight method is used to calculate the first-level index score of the user terminal according to the questionnaire questions of the second-level index. keywords: brand; calculate; data; entropy; index; level; method; power; value; weight cache: fcis-9459.pdf plain text: fcis-9459.txt item: #856 of 872 id: fcis-9466 author: Zhang, Yujie; Li, Jiawei title: Research on Real-time Simulation of Automobile Production Line based on Discrete Event and Multiagent date: 2023 words: 3380 flesch: 46 summary: A series of achievements have been made in researching automobile production line simulation at home and abroad. During operation, the simulation system can simulate the inventory status, order demand, and production line operation of materials. keywords: agent; automobile; figure; line; model; module; operation; process; production; simulation; system; time cache: fcis-9466.pdf plain text: fcis-9466.txt item: #857 of 872 id: fcis-9468 author: Jiang, Jianguo; Yang, Lili title: Research on Optimal Configuration of Distributed Generation based on Multi-scenario Analysis date: 2023 words: 5600 flesch: 51 summary: The actual output power of the fan is closely related to the wind speed, and the specific relationship can be expressed as follows: WTG WTG WTG 0 0 or ci co r ci ci r r ci r r co v v v v v v P P v v v v v P v v v             (2) WTG WTG WTGtan P Q   (3) Where WTG rP is the rated active power of the fan; civ , rv , cov are the cut-in wind speed, rated wind speed and cut-out wind speed of the fan respectively; WTG is the power factor angle for wind power generation. I DGk DGkjm k j N r r C C P r         (15) Where r is the cash discount rate; m is the planning period of DG; k is the type of DG incorporated into the power grid (1 stands for wind power generation; 2 stands for photovoltaic power generation); DGkN is the node set incorporated into the power grid; I DGkC is the unit capacity investment cost of k types of DG; I DGkjP is the installation capacity of the type k DG of the node j to be installed. keywords: algorithm; cost; distribution; generation; load; model; node; optimization; planning; power cache: fcis-9468.pdf plain text: fcis-9468.txt item: #858 of 872 id: fcis-9473 author: Lu, Yukai; Zhao, Yongbiao; Ju, Yun title: Improved Detection of Ice Accretion Status on Transmission Lines Using YOLOv5s date: 2023 words: 3134 flesch: 43 summary: Ice accretion detection on transmission lines is one of the important research directions for the State Grid Company. After years of domestic and international research, it has been found that utilizing image processing technology for ice accretion detection on transmission lines is a more intuitive and reliable method compared to other approaches. keywords: accretion; detection; feature; ice; image; information; map; model; transmission; yolov5s cache: fcis-9473.pdf plain text: fcis-9473.txt item: #859 of 872 id: fcis-9478 author: Wu, Dan; Ye, Shenglan title: Research on Water Extraction from Remote Sensing Images based on Ada Boost Algorithm date: 2023 words: 1936 flesch: 45 summary: Aiming at the existing problems in remote sensing image water extraction, a water extraction method based on Ada Boost algorithm is proposed. China Abstract: The extraction of water in remote sensing image is a key step in the application of remote sensing image. keywords: algorithm; extraction; image; results; sensing; water cache: fcis-9478.pdf plain text: fcis-9478.txt item: #860 of 872 id: fcis-9479 author: Wang, Rong title: Fake News Detection based on Deep Learning date: 2023 words: 3131 flesch: 57 summary: While learning news text features and visual information, the SAFE[18] model also learned the intrinsic connection between text content and vision to predict fake news. Status of Domestic and International Research As deep learning continues to make progress, more and more researchers are studying fake news detection based on neural networks. keywords: detection; features; figure; information; model; multimodal; news; text; training; xgboost cache: fcis-9479.pdf plain text: fcis-9479.txt item: #861 of 872 id: fcis-9489 author: Shi, Quan title: The Empirical Analysis of the EU Artificial Intelligence Act date: 2023 words: 2692 flesch: 24 summary: In this context, the EU AI Act applies not only to providers of specific AI systems placed on the market or put into service within the EU and users who utilize AI systems for commercial purposes within the EU but also to providers and 110 users of AI systems located outside the EU if their outcomes are used within the EU (Article 2(1)(a), (b), (c) and Article 3(4) of the AI Act).Regarding regulatory bodies, the act establishes the European Artificial Intelligence Board composed of representatives from member states and the European Commission to ensure effective cooperation between this board, national regulatory authorities, and the European Commission. This risk-based approach determines the intensity of regulation based on the risk level of AI systems to fundamental rights in the EU, particularly imposing obligations on high-risk AI systems while prescribing modified obligations and codes of conduct for other AI systems. keywords: act; artificial; intelligence; risk; systems cache: fcis-9489.pdf plain text: fcis-9489.txt item: #862 of 872 id: fcis-9673 author: Huang, Chunxiu title: Bearing Fault Diagnosis based on Residual Network Attention Mechanism date: 2023 words: 2202 flesch: 49 summary: In recent years, deep learning technology has been widely studied in rolling bearing fault diagnosis and achieved good results. The experimental results show that the method greatly improves the efficiency of rolling bearing fault diagnosis. keywords: attention; bearing; diagnosis; fault; model; network cache: fcis-9673.pdf plain text: fcis-9673.txt item: #863 of 872 id: fcis-9700 author: Zhang, Zhichao title: Nurse Scheduling Algorithms based on Different Scenarios date: 2023 words: 3281 flesch: 60 summary: The workload of medical workers is becoming increasingly huge, and many hospitals use manual methods for nurse scheduling. Nurse scheduling is an important part of nursing management, which is the foundation for completing nursing work and meeting the multi-dimensional needs of patients keywords: a1.0 a1.0; a2.0; a2.0 a2.0; a3.0; algorithm; number; nurse; scheduling; shift cache: fcis-9700.pdf plain text: fcis-9700.txt item: #864 of 872 id: fcis-9730 author: Cong, Xiaohan; Li, Shixin; Chen, Fankai; Liu, Chen; Meng, Yue title: A Review of YOLO Object Detection Algorithms based on Deep Learning date: 2023 words: 3122 flesch: 55 summary: Abstract: Object detection is a research hotspot in the field of computer vision, and YOLO series shows good performance in object detection, and has been widely used in robot vision, unmanned driving and other fields in recent years. An overview of object detection algorithms based on Deep Learning [J]. keywords: algorithms; detection; learning; model; network; object; performance; target; yolo; yolov7 cache: fcis-9730.pdf plain text: fcis-9730.txt item: #865 of 872 id: fcis-9746 author: Chen, Caiming; Wang, Fenglin title: Exploring the Innovative Application of Azure Cloud Computing Platform in Cross-border E-commerce Operation: -- Taking China and Southeast Asia Trade as an Example date: 2023 words: 4830 flesch: 42 summary: We expect this study to provide a reference for Cross-border E-commerce enterprises to adopt cloud technology, improve operational efficiency and reduce operating costs, and provide theoretical support for future related research. Its flexible and scalable features make it an important tool for Cross-border E-commerce enterprises around the world to support and expand their business operations [6][7]. keywords: asia; azure; cloud; commerce; computing; data; enterprises; market; operations; southeast cache: fcis-9746.pdf plain text: fcis-9746.txt item: #866 of 872 id: fcis-9761 author: Xu, Xiaoxiao title: A Lightweight Dual-Branch Image Dehazing Network based on Associative Learning date: 2023 words: 2406 flesch: 51 summary: [17], which is widely used in the field of image dehazing and consists of haze images synthesized using prior information. Image dehazing provides a means to obtain clearer and more accurate image information. keywords: dehazing; haze; ieee; image; network; transactions cache: fcis-9761.pdf plain text: fcis-9761.txt item: #867 of 872 id: fcis-985 author: Zhang, Ji; Ran, Zijian title: Face and Gender Detection Based on BP Neural Network Algorithm date: 2022 words: 2090 flesch: 54 summary: Abstract: Face recognition technology has a wide range of applications in real life, and many applications can be developed on the basis of face recognition, such as gender recognition, age recognition, face comparison, and beauty image decoration. Face recognition is a form of biometric technology, which involves many methods in pattern recognition, computer vision, psychology, physiology, and cognitive science. keywords: face; input; layer; network; recognition cache: fcis-985.pdf plain text: fcis-985.txt item: #868 of 872 id: fcis-9856 author: Chen, Wei; Shen, Haiwei title: A Super-resolution Algorithm for Remote Sensing Images based on Data Enhancement and Generative Adversarial Networks date: 2023 words: 4118 flesch: 38 summary: The degradation model uses randomly mixing and washing degradation factors (such as blur, downsampling, noise, etc.) to simulate the real imaging process to generate realistic low-resolution images combined with the original images in pairs for training; meanwhile, a new image processing architecture based on generative adversarial networks is proposed to enhance image details and preserve image features through ResNet34 and mini-CNN networks, and the method can better enhance the effect of super-resolution reconstruction of remote sensing images. The paper addresses the problem of poor recovery effect of current super-resolution reconstruction algorithms in the field of real remote sensing images, and adopts the method of randomly mixing and washing degradation factors to simulate the imaging process of real remote sensing images to generate low-resolution remote sensing images; meanwhile, a super- resolution reconstruction algorithm based on generative adversarial network is improved to enhance the texture details of remote sensing images with ResNet34 and CNN as the basis, so as to be able to extract more rich features from images to extract richer features, and the effects of the degradation model and super-resolution reconstruction model are verified on the dataset UC Merced and the real remote sensing dataset Alsat2B. keywords: degradation; feature; images; model; noise; reconstruction; resolution; sensing; super cache: fcis-9856.pdf plain text: fcis-9856.txt item: #869 of 872 id: fcis-9866 author: Chen, Wei; Chen, Xiangyu title: Design and Implementation of a C++Based Hotel Management System date: 2023 words: 3424 flesch: 37 summary: [2] The hotel management system as a whole needs the following classes, permission class includes customer class, administrator class, front desk staff class and general staff class, permission class is mainly through different permissions to distinguish between staff and customers, as well as the functions between various employees; information class includes room information, customer information, staff information, hotel information, etc., which is mainly used to store relevant information, combined with the previous permission class, so that people with different permissions can access different information. Front desk staff can register and confirm customers' information at check-in, give feedback to customers' room reservation, help call service staff or maintenance staff, check and update hotel room information, respond to customers' service requests after check-in, and help settle accounts after customers leave the hotel, record customers' opinions and comments, etc. according to the rights assigned by the administrator. keywords: customer; hotel; information; management; number; room; staff; system cache: fcis-9866.pdf plain text: fcis-9866.txt item: #870 of 872 id: fcis-9900 author: Zhang, Heng; Fu, Wei; Wu, Ke title: Review of Small Target Detection based on Deep Learning date: 2023 words: 5358 flesch: 50 summary: This paper first starts with the development of target detection briefly describes the obstacles to the development of target detection, and then transitions to small target detection. Small target detection has always been a difficult point and research hotspot. keywords: computer; dataset; detection; enhancement; feature; ieee; image; information; model; network; object; small; target; target detection cache: fcis-9900.pdf plain text: fcis-9900.txt item: #871 of 872 id: fcis-9941 author: Xu, Hantao; Ye, Xia; Yang, Zhangping; Zhao, Pujie title: A Survey of Language Priors for Visual Question Answering date: 2023 words: 5543 flesch: 52 summary: [22] believe that the existing work on alleviating language priors for visual question answering models cannot explain the reasons for language bias well. Due to the continuous improvement of relevant large-scale standard data sets, a large number of visual questions answering research results have been released one after another, and the accuracy rate of the visual question answering model based on deep learning on the data set has been continuously improved. keywords: answering; conference; data; et al; image; language; model; question; training; vqa cache: fcis-9941.pdf plain text: fcis-9941.txt item: #872 of 872 id: fcis-9970 author: Chen, Ji; Xiao, Ao; Li, Zhihui; Liu, Jiaqing; Feng, Mengyuan; Xue, Hao; Gu, Siwen title: Fault Diagnosis of Hydraulic System based on SOM Neural Network date: 2023 words: 2432 flesch: 58 summary: Schematic diagram of horizontal outrigger hydraulic circuit A horizontal outrigger hydraulic circuit of a construction machine was applied as a test device to verify the application of SOM neural network in fault diagnosis. I D1 26 26 0 12 0.04 14 0.08 14 21 19 D2 25 24 1.6 18 0.05 16 0.002 16 25 19 2. Fault Diagnosis Steps based on SOM Neural Network The application of SOM neural networks in fault diagnosis is generally divided into the following steps keywords: diagnosis; fault; figure; hydraulic; network; som cache: fcis-9970.pdf plain text: fcis-9970.txt