item: #1 of 82
          id: keds-11100
      author: Rosyid, Harits Ar; Aniendya, Mutyara Whening; Herwanto, Heru Wahyu
       title: Comparison of Indonesian Imports Forecasting by Limited Period Using SARIMA Method
        date: 2019-12-23
       words: 5444
      flesch: 63
     summary: The output of the function is forecasting value, lower limit and upper limit of forecasting. Import dataset of ARIMA model candidates’ Ljung-box value ARIMA Model Ljung-Box (1,1,0)(1,1,0)12 0.3167 (2,1,0)(1,1,0)12 0.7164 (3,1,0)(1,1,0)12 0.5898 (1,1,0)(0,1,1)12 0.1658 (2,1,0)(0,1,1)12 0.6858 (3,1,0)(0,1,1)12 0.6807 (0,1,1)(1,1,0)12 0.09715 (0,1,2)(1,1,0)12 0.4701 (0,1,3)(1,1,0)12 0.9819 (0,1,1)(0,1,1)12 0.07206 (0,1,2)(0,1,1)12 0.5218 (0,1,3)(0,1,1)12 0.9662 Fig. 4.
    keywords: acf; arima; data; dataset; forecasting; import; mape; model; plot; time; value
       cache: keds-11100.pdf
  plain text: keds-11100.txt

        item: #2 of 82
          id: keds-1236
      author: Purnawansyah, Purnawansyah; Haviluddin, Haviluddin; Alfred, Rayner; Gaffar, Achmad Fanany Onnilita
       title: Network Traffic Time Series Performance Analysis Using Statistical Methods
        date: 2017-12-31
       words: 3041
      flesch: 54
     summary: This present study aims at juxtaposing forecasting result using time series data in accordance with three statistical methods i.e. Decomposition, Winter’s exponential smoothing and ARIMA. The basic principle of time series decomposition method is to disintegrate time series data in several patterns and identified those time series segregated, then discovered it separately.
    keywords: arima; data; exponential; forecasting; model; series; smoothing; time
       cache: keds-1236.pdf
  plain text: keds-1236.txt

        item: #3 of 82
          id: keds-12480
      author: Nugroho, I Made Riyan Adi; Sentana, I Wayan Budi
       title: Query Rewriting with Thesaurus-Based for Handling Semantic Heterogeneity in Database Integration
        date: 2020-06-30
       words: 2866
      flesch: 61
     summary: Get source schema is a process of getting data source which produced by extraction schema stage. [3] A. Aslam, S. Khan, and K. Latif, “Semantic based query rewriting in heterogeneous sources,” Proc. - 4th IEEE Int. Conf.
    keywords: data; fig; keyword; matching; process; query; rewriting; schema; semantic; source
       cache: keds-12480.pdf
  plain text: keds-12480.txt

        item: #4 of 82
          id: keds-1289
      author: Wijaya, Novan
       title: Capital Letter Pattern Recognition in Text to Speech by Way of Perceptron Algorithm
        date: 2017-12-31
       words: 2747
      flesch: 53
     summary: Sample data of this study is a collection of caputured capital letter image by webcam which then be processed using PC and programs as well as image segmentation techniques. Upon image cropping process, image size would be rendered into 20 x 20 pixel size (Fig.8).
    keywords: data; fig; image; letter; pattern; perceptron; process; system
       cache: keds-1289.pdf
  plain text: keds-1289.txt

        item: #5 of 82
          id: keds-1375
      author: Hozairi, Hozairi; Krisnafi, Yaser
       title: Decision Support System Determination of Main Work Unit In WPP-711 Using Fuzzy TOPSIS
        date: 2017-12-31
       words: 4699
      flesch: 66
     summary: Square value on each alternative Value Benefit Cost Square - 1 0.002 0.138 Square - 2 0.065 0.030 Square - 3 0.135 0.005 Square - 4 0.100 0.033 Square - 5 0.091 0.034 Square - 6 0.105 0.027 Square - 7 0.016 0.075 Square - 8 0.074 0.024 Square - 9 0.010 0.110 Square - 10 0.085 0.028 Square - 11 0.070 0.038 14 Hozairi and Y. Krisnafi. The final phase in the calculation of TOPSIS is determining preference value for each alternative given according to the following equation.
    keywords: alternative; criteria; ideal; matrix; preference; solution; square; table; topsis; unit; value; working
       cache: keds-1375.pdf
  plain text: keds-1375.txt

        item: #6 of 82
          id: keds-1376
      author: Ardiansah, Jevri Tri; Wibawa, Aji Prasetya; Widyaningtyas, Triyanna; Yasuhisa, Okazaki
       title: SQL Logic Error Detection by Using Start End Mid Algorithm
        date: 2017-12-31
       words: 3690
      flesch: 65
     summary: Results and Discussion This system is able to do prediction about user's mistake regarding SQL logic error. That conclusion is supported by another research about SQL errors.
    keywords: data; error; logic; select; sql; syntax; system; table
       cache: keds-1376.pdf
  plain text: keds-1376.txt

        item: #7 of 82
          id: keds-1386
      author: Kurniawan, Fachrul; Umayah, Binti; Hammad, Jihad; Nugroho, Supeno Mardi Susiki; Hariadi, Mochammad
       title: Market Basket Analysis to Identify Customer Behaviours by Way of Transaction Data
        date: 2017-12-31
       words: 2252
      flesch: 51
     summary: From that statement, there has a strong relation to the study of customer transaction data database to determine the habit of a purchased product with what product, thus, association rule is frequently referred as market basket analysis In these recent years, transaction data have been commonly used as research and analysis objects for researchers.
    keywords: analysis; basket; data; market; transaction; 𝐶𝑜𝑛𝑡𝑎𝑖𝑛𝑠 𝐴; 𝑇𝑟𝑎𝑛𝑠𝑎𝑐𝑡𝑖𝑜𝑛
       cache: keds-1386.pdf
  plain text: keds-1386.txt

        item: #8 of 82
          id: keds-14402
      author: Athiyah, Ummi; Muhammad, Arif Wirawan; Azhari, Ahmad
       title: Human Intestinal Condition Identification based-on Blended Spatial and Morphological Feature using Artificial Neural Network Classifier
        date: 2020-06-30
       words: 3786
      flesch: 51
     summary: Artificial neural network training result for blended feature U. Athiyah et al. / The dataset is divided into three parts to avoid bias on the results of artificial neural network training.
    keywords: cancer; endoscopic; feature; fig; image; input; network; neural; process; table; training; value
       cache: keds-14402.pdf
  plain text: keds-14402.txt

        item: #9 of 82
          id: keds-14602
      author: Prahara, Adhi; Ismi, Dewi Pramudi; Azhari, Ahmad
       title: Parallelization of Partitioning Around Medoids (PAM) in K-Medoids Clustering on GPU
        date: 2020-06-30
       words: 4987
      flesch: 63
     summary: c) Compute the total cost of swapping that is the difference between the AEC calculated using the current medoid data point and the AEC calculated using the non-medoid data point selected in step b. One of the technologies that used to develop parallel k-medoids clustering is Hadoop-MapReduce [18][19][20][21][22][23].
    keywords: algorithm; clustering; data; distance; gain; gpu; index; medoids; number; pam
       cache: keds-14602.pdf
  plain text: keds-14602.txt

        item: #10 of 82
          id: keds-14682
      author: Priambodo, Bagus; Mahmudy, Wayan Firdaus; Rahman, Muh Arif
       title: Earthquake Magnitude and Grid-Based Location Prediction using Backpropagation Neural Network
        date: 2020-06-30
       words: 6501
      flesch: 61
     summary: [24] I. Wahyuni, N. R. Adam, W. F. Mahmudy, and A. Iriany, ―Modeling backpropagation neural network for rainfall prediction in tengger east Java,‖ in Proceedings - 2017 International Conference on Sustainable Information Engineering and Technology, SIET 2017, 2018, vol. [8] F. A. Huda, W. F. Mahmudy, and H. Tolle, “Android malware detection using backpropagation neural network,” Indones.
    keywords: backpropagation; data; earthquake; error; function; layer; magnitude; network; neural; rate; vol
       cache: keds-14682.pdf
  plain text: keds-14682.txt

        item: #11 of 82
          id: keds-15279
      author: Dhunny, A. Zaynah; Seebocus, Reena Hansa; Allam, Zaheer; Chuttur, Mohammad Yasser; Eltahan, Muhammed; Mehta, Harsh
       title: Flood Prediction using Artificial Neural Networks: Empirical Evidence from Mauritius as a Case Study
        date: 2020-06-30
       words: 5548
      flesch: 47
     summary: Recorded rainfall data skyrocketed for the central regions (Providence, Quatre Bornes and Vacoas), while other regions recorded higher rainfall data than for the same period in 2017. Here also, results indicated that the ANN model provided fairly good accuracy in predicting rainfall data.
    keywords: ann; data; flood; forecasting; mauritius; model; network; neural; prediction; rainfall; regions; temperature; vol; weather
       cache: keds-15279.pdf
  plain text: keds-15279.txt

        item: #12 of 82
          id: keds-15449
      author: Sendari, Siti; Zaeni, Ilham Ari Elbaith; Lestari, Dian Candra; Hariyadi, Hanny Prasetya
       title: Opinion Analysis for Emotional Classification on Emoji Tweets using the Naïve Bayes Algorithm
        date: 2020-06-30
       words: 5210
      flesch: 60
     summary: The algorithm performance calculation was a test for Emoji tweet data. This is made clear by the results of prediction errors on Emoji text data totaling 28 data.
    keywords: classification; data; emoji; probability; testing; text; tweets; twitter; value; word
       cache: keds-15449.pdf
  plain text: keds-15449.txt

        item: #13 of 82
          id: keds-15708
      author: Mahmudy, Wayan Firdaus; Pardede, Andreas; Widodo, Agus Wahyu; Rahman, Muh Arif
       title: Efficient Scheduling of Plantation Company Workers using Genetic Algorithm
        date: 2020-12-31
       words: 4377
      flesch: 64
     summary: The assessment is used to measure how good the chromosome is for worker scheduling. Knowledge Engineering and Data Science 2020, 3 (2): 60–66 65 IV. Conclusion Genetic algorithms for optimizing worker scheduling can be implemented with integer chromosome representation.
    keywords: algorithm; fitness; population; scheduling; value; vol
       cache: keds-15708.pdf
  plain text: keds-15708.txt

        item: #14 of 82
          id: keds-15795
      author: Sleeman, Jumah Y.J; Hammad, Jehad Abdulhamid
       title: A Review of Accessing Big Data with Significant Ontologies
        date: 2020-12-31
       words: 5776
      flesch: 62
     summary: The main aim of ontology rewriting query is to solve the problem of query answering that comes from the end-user. 2) Mapping layer that is able to solve the problems arising from the difference between the basic elements managed by data sources and the elements managed by the ontology.
    keywords: access; data; information; knowledge; mapping; obda; ontology; queries; query; sources; vol
       cache: keds-15795.pdf
  plain text: keds-15795.txt

        item: #15 of 82
          id: keds-15835
      author: Faiz, Faadihilah Ahnaf; Azhari, Ahmad
       title: Tanned and Synthetic Leather Classification Based on Images Texture with Convolutional Neural Network
        date: 2020-12-31
       words: 6232
      flesch: 57
     summary: The images acquisition processes in this research used a smartphone camera to capture the leather images with distances between the object and the camera lens about 10-20 centimeters and added external flash lamp for help increase the sharpness of leather images. Leather images dataset 80 F.A. Faiz and A. Azhari / Knowledge Engineering and Data Science 2020, 3 (2): 77–88 C. Image Segmentation Image Segmentation in this research used to changes the RGB images into grayscale images.
    keywords: classification; conf; convolutional; data; ieee; images; int; layer; leather; network; neural; pooling; research; training
       cache: keds-15835.pdf
  plain text: keds-15835.txt

        item: #16 of 82
          id: keds-16136
      author: Gama, Adie Wahyudi Oktavia; Widnyani, Ni Made
       title: Simple Modification for an Apriori Algorithm With Combination Reduction and Iteration Limitation Technique
        date: 2020-12-31
       words: 6459
      flesch: 58
     summary: Apriori algorithm is one of the methods with regard to association rules in data mining. Apriori algorithm takes an iterative approach, that is, generating k-itemset that is used to form the next (k + 1) -itemset.
    keywords: algorithm; apriori; association; data; frequent; itemset; rules; shirt; trousers
       cache: keds-16136.pdf
  plain text: keds-16136.txt

        item: #17 of 82
          id: keds-1720
      author: Sari, Nadia Roosmalita; Sarwani, Moh. Zoqi; Aulia, Yudha Alif; Mahmudy, Wayan Firdaus
       title: Signature Pattern Recognition using Kohonen Network
        date: 2018-08-23
       words: 2841
      flesch: 63
     summary: For example, signature data will undergo the feature values extracting process with 15x15 grids 225 segments. Fig. 6 illustrates the architecture of SOM Kohonen and Fig. 7 shows the diagram of signature recognition process.
    keywords: data; image; kohonen; method; process; recognition; signature; som; study
       cache: keds-1720.pdf
  plain text: keds-1720.txt

        item: #18 of 82
          id: keds-18291
      author: Pujianto, Utomo; Akbar, Muhammad Iqbal; Lassela, Niendhitta Tamia; Sutaji, Deni
       title: The Effect of Resampling on Classifier Performance: an Empirical Study
        date: 2022-06-07
       words: 7269
      flesch: 59
     summary: Each dataset will go through 3 processing stages: the resampling process, the classification process, and the significance testing process between performance evaluation values of the combination of classifier and the resampling using paired t-test. Result of paired t-test between a combination of classifier and resampling based on accuracy values Paired t-test results based on accuracy values as shown in Figure 5, the combination of NN Algorithms without resampling gives the most significant results than the other 11 combinations.
    keywords: algorithm; class; classification; classifier; data; dataset; layer; oversampling; performance; resampling; results; smote; test; undersampling; value
       cache: keds-18291.pdf
  plain text: keds-18291.txt

        item: #19 of 82
          id: keds-18620
      author: Fajri, Diny Melsye Nurul; Mahmudy, Wayan Firdaus; Yulianti, Titiek
       title: Detection of Disease and Pest of Kenaf Plant Based on Image Recognition with VGGNet19
        date: 2021-06-30
       words: 5365
      flesch: 56
     summary: Conclusion In conclusion, the design of Kenaf plant disease & pest detection can be done by developing Image Recognition technology by coding using the Python programming language with open source Keras which is run on the TensorFlow machine learning platform. Leaf recognition training accuracy with the epoch approach is up to 100 Epoch Train Accuracy Train Loss Time 1 0.7672 0.525 52s 2 0.8307 0.3751 57s 3 0.8594 0.3038 59s 4 0.8942 0.1964 59s 5 0.9032 0.1389 59s … 96 1.0000 0.00008467 64s 97 1.0000 0.000091677 63s 98 1.0000 0.000078224 63s 99 1.0000 0.000098397 64s 100 1.0000 0.000060537 63s Table 2.
    keywords: accuracy; data; deep; disease; figure; image; kenaf; layer; leaf; learning; network; recognition; training; value
       cache: keds-18620.pdf
  plain text: keds-18620.txt

        item: #20 of 82
          id: keds-19166
      author: Santoso, Joan; Setiawan, Esther Irawati; Purwanto, Christian Nathaniel; Kurniawan, Fachrul
       title: Indonesian Sentence Boundary Detection using Deep Learning Approaches
        date: 2021-06-30
       words: 7861
      flesch: 57
     summary: Sentence boundary detection is used to split every sentence in a document. Several studies use sentence boundary detection for text pre-processing.
    keywords: boundary; conference; detection; end; example; language; lstm; mark; problem; proceedings; processing; sentence; stop; text; token; use; vol; 𝑓𝑤𝑑
       cache: keds-19166.pdf
  plain text: keds-19166.txt

        item: #21 of 82
          id: keds-19547
      author: Astawa, I Nyoman Gede Arya; Radhitya, Made Leo; Ardana, I Wayan Raka; Dwiyanto, Felix Andika
       title: Face Images Classification using VGG-CNN
        date: 2021-06-30
       words: 2806
      flesch: 46
     summary: Hopefully, this research significantly contributes to knowledge development, especially in face image classification. Specifically, image classification is part of facial recognition processes, which is an actual problem in computer vision [3].
    keywords: accuracy; classification; data; face; image; model; process; recognition; training; vgg
       cache: keds-19547.pdf
  plain text: keds-19547.txt

        item: #22 of 82
          id: keds-19598
      author: Albar, Albar; Hendrick, Hendrick; Hidayat, Rahmad
       title: Segmentation Method for Face Modelling in Thermal Images
        date: 2020-12-31
       words: 2743
      flesch: 65
     summary: Face images were recorded by using a FLIR Lepton thermal camera, which has specification as a military standard device [12]. In this research, we proposed a segmentation method, Mask RCNN, to create a face model from thermal images.
    keywords: data; dataset; detection; face; images; mask; model; rcnn; vol
       cache: keds-19598.pdf
  plain text: keds-19598.txt

        item: #23 of 82
          id: keds-20008
      author: Purnawansyah, Purnawansyah; Haviluddin, Haviluddin; Darwis, Herdianti; Azis, Huzain; Salim, Yulita
       title: Backpropagation Neural Network with Combination of Activation Functions for Inbound Traffic Prediction
        date: 2021-06-30
       words: 4220
      flesch: 58
     summary: Based on the result, in terms of a single form of activation function, although sigmoid provides the least RMSE and MSE values, the ReLu function is more superior in learning the high traffic pattern with a learning rate of 0.9. Keywords: Backpropagation Combination of activation function Forecasting Inbound Traffic ReLu-Sigmoid ReLu-tanh http://u.lipi.go.id/1502081730 http://u.lipi.go.id/1502081046 https://doi.org/10.17977/um018v4i12021p14-28 http://journal2.um.ac.id/index.php/keds mailto:keds.journal@um.ac.id https://creativecommons.org/licenses/by-sa/4.0/ https://sinta.ristekbrin.go.id/journals/detail?id=6662 https://creativecommons.org/licenses/by-sa/4.0/ Purnawansyah et al. /
    keywords: activation; data; function; learning; network; neural; rate; relu; sigmoid; traffic
       cache: keds-20008.pdf
  plain text: keds-20008.txt

        item: #24 of 82
          id: keds-20891
      author: Wibawa, Aji Prasetya; Fithri, Hidayah Kariima; Zaeni, Ilham Ari Elbaith; Nafalski, Andrew
       title: Generating Javanese Stopwords List using K-means Clustering Algorithm
        date: 2020-12-31
       words: 3348
      flesch: 66
     summary: In this case, 680 words is labeled as stop words, where 13704 words are non-stopwords. The words are excluded from the bag of words to speed up the text classification process
    keywords: int; javanese; list; non; stopwords; vol
       cache: keds-20891.pdf
  plain text: keds-20891.txt

        item: #25 of 82
          id: keds-21183
      author: Masouleh, Marzieh Faridi; Bagheri, Ahmad
       title: Forecasting Stock Exchange Data using Group Method of Data Handling Neural Network Approach
        date: 2021-06-30
       words: 6879
      flesch: 60
     summary: Thus, this research makes use of the GMDH neural network algorithm to forecast stock exchange data. [25] A. Carriero, G. Kapetanios, and M. Marcellino, “Forecasting exchange rates with a large Bayesian VAR,” Int.
    keywords: algorithm; approach; data; doi; error; exchange; forecasting; gmdh; method; model; network; neural; rates; vol
       cache: keds-21183.pdf
  plain text: keds-21183.txt

        item: #26 of 82
          id: keds-21527
      author: Ahammed, Toukir; Ahmed, Sumon; Khan, Mohammed Shafiul Alam
       title: Do Missing Link Community Smell Affect Developers Productivity: An Empirical Study
        date: 2021-06-30
       words: 4518
      flesch: 54
     summary: Missing link community smell can create the knowledge gap among developers in the development community due to a lack of communication [5]. Missing link community smell refers to when two developers collaborate in a part of source code but do not communicate with each other [3].
    keywords: community; developers; engineering; link; productivity; projects; smelly; software; source
       cache: keds-21527.pdf
  plain text: keds-21527.txt

        item: #27 of 82
          id: keds-22181
      author: Suhana, Rizka; Mahmudy, Wayan Firdaus; Budi, Agung Setia
       title: Fish Image Classification Using Adaptive Learning Rate In Transfer Learning Method
        date: 2022-06-07
       words: 5088
      flesch: 57
     summary: Conservation data in video, then processed to produce fish image data. The fish image will be analyzed by experts, including what type of fish image is.
    keywords: accuracy; architecture; classification; data; fish; image; layer; learning; mobilenet; model; phase; table; value
       cache: keds-22181.pdf
  plain text: keds-22181.txt

        item: #28 of 82
          id: keds-24499
      author: Md Jamil, Abu Rafe; Nower, Naushin
       title: A Comprehensive Analysis of Reward Function for Adaptive Traffic Signal Control
        date: 2021-12-15
       words: 8048
      flesch: 59
     summary: In this type of reward function, various traffic features are combined in different ways to optimize parameters. Different types of reward functions have been proposed in the literature, and none of them compares among these reward functions.
    keywords: agent; configuration; control; function; learning; objective; reinforcement; reward; reward function; signal; time; traffic
       cache: keds-24499.pdf
  plain text: keds-24499.txt

        item: #29 of 82
          id: keds-24529
      author: Saleh, Abdulrazak Yahya; Xian, Lau Khai
       title: Stress Classification using Deep Learning with 1D Convolutional Neural Networks
        date: 2021-12-15
       words: 4300
      flesch: 48
     summary: The implementation is multivariate analysis to evaluate 1D CNNs deep learning model. This study aims to use stress datasets to anticipate an accurate output; society will use the outcomes.
    keywords: classification; cnns; data; dataset; input; learning; model; networks; neural; stress; vol
       cache: keds-24529.pdf
  plain text: keds-24529.txt

        item: #30 of 82
          id: keds-24585
      author: Handayani, Anik Nur; Herwanto, Heru Wahyu; Chandrika, Katya Lindi; Arai, Kohei
       title: Recognition of Handwritten Javanese Script using Backpropagation with Zoning Feature Extraction
        date: 2021-12-15
       words: 5699
      flesch: 56
     summary: 𝐴𝑐𝑐𝑢𝑟𝑎𝑐𝑦 = 𝛴 𝑁 𝑐𝑜𝑟𝑟𝑒𝑐𝑡 Σ N (6) where Σ 𝑁 correct is the number of image data that are classified correctly, and Σ 𝑁 is the number of available image data. Backpropagation Neural Network Architecture Java Script Recognition Fig.
    keywords: backpropagation; data; feature; image; learning; network; neural; neurons; number; vol
       cache: keds-24585.pdf
  plain text: keds-24585.txt

        item: #31 of 82
          id: keds-24968
      author: Yaman, Aris; Kartika, Yulia Aris; Indrawati, Ariani; Akbar, Zaenal; Malik, Lindung Parningotan; Wardani, Wita; Djarwaningsih, Tutie; Mahendra, Taufik; Saleh, Dadan Ridwan
       title: Non-Gaussian Analysis of Herbarium Specimen Damage to Optimize Specimen Collection Management
        date: 2022-11-07
       words: 7084
      flesch: 51
     summary: However, manual investigation of the causes of herbarium collection damage requires a lot of effort and time. Only a few studies have attempted to investigate the causes of herbarium collection damage.
    keywords: collection; damage; data; excoecaria; herbarium; insects; model; modeling; process; regression; response; species; specimens; storage; variable
       cache: keds-24968.pdf
  plain text: keds-24968.txt

        item: #32 of 82
          id: keds-24971
      author: Setyati, Endang; Az, Suharyono; Hudiono, Subroto Prasetya; Kurniawan, Fachrul
       title: CNN based Face Recognition System for Patients with Down and William Syndrome
        date: 2022-03-23
       words: 3919
      flesch: 56
     summary: Down syndrome and Williams syndrome can be diagnosed by detecting the face, or facial characteristics, such as picking up particular facial traits [9] D. Dimitriou, H. C. Leonard, A. Karmiloff-Smith, M. H. Johnson, and M. S. C. Thomas, “Atypical development of configural face recognition in children with autism, Down syndrome and Williams syndrome,” J. Intellect.
    keywords: cnn; data; syndrome; vol; williams
       cache: keds-24971.pdf
  plain text: keds-24971.txt

        item: #33 of 82
          id: keds-25035
      author: Ismail, Amelia Ritahani; Affendy, Nur Shairah Muhd; Ismail, Ahsiah; Puzi, Asmarani Ahmad
       title: Social Distancing Monitoring System using Deep Learning
        date: 2022-11-07
       words: 4828
      flesch: 53
     summary: Social distancing detection for the test video Fig. 9. Social distancing detection for the test video A.R. Ismail et al. / Knowledge Engineering and Data Science 2022, 5 (1): 17–26 25 was taken from the video for 21 seconds and 531 frames.
    keywords: cnn; dataset; detection; distancing; model; network; object; person; ssd; system; yolo
       cache: keds-25035.pdf
  plain text: keds-25035.txt

        item: #34 of 82
          id: keds-25384
      author: Wibowo, Merlinda; Quix, Christoph; Hussien, Nur Syahela; Yuliansyah, Herman; Adhinata, Faisal Dharma
       title: Similarity Identification of Large-scale Biomedical Documents using Cosine Similarity and Parallel Computing
        date: 2022-02-04
       words: 4953
      flesch: 49
     summary: In this stage, the identification results of document similarities will be represented in a graph, statistical table, and web application. Execution time of document similarity application http://journal2.um.ac.id/index.php/keds 116 M. Wibowo et al. /
    keywords: abstract; application; cosine; data; documents; heading; mesh; pubmed; result; similarity; text; vol
       cache: keds-25384.pdf
  plain text: keds-25384.txt

        item: #35 of 82
          id: keds-25393
      author: Trang, Kien; Nguyen, An Hoang
       title: A Comparative Study of Machine Learning-based Approach for Network Traffic Classification
        date: 2022-01-01
       words: 6651
      flesch: 48
     summary: [9] Z. Fan and R. Liu, Investigation of machine learning based network traffic classification, 2017 International Symposium on Wireless Communication Systems (ISWCS), pp. [9] Z. Fan and R. Liu, Investigation of machine learning based network traffic classification, 2017 International Symposium on Wireless Communication Systems (ISWCS), pp. 1-6, August 2017.
    keywords: classification; conference; data; dataset; international; internet; learning; machine; model; network; traffic; traffic classification; vpn
       cache: keds-25393.pdf
  plain text: keds-25393.txt

        item: #36 of 82
          id: keds-25719
      author: Kusuma, Edi Jaya; Pantiawati, Ika; Handayani, Sri
       title: Melanoma Classification based on Simulated Annealing Optimization in Neural Network
        date: 2022-03-15
       words: 3929
      flesch: 54
     summary: [17] D. Chai and A. Bouzerdoum, “A Bayesian approach to skin color classification in YCbCr color space,” in 2000 TENCON Proceedings. One cancer disease that commonly arises in the country with a high UV (Ultraviolet) light index is skin cancer
    keywords: accuracy; annealing; bpnn; cancer; color; data; model; network; skin; vol
       cache: keds-25719.pdf
  plain text: keds-25719.txt

        item: #37 of 82
          id: keds-25980
      author: Prahara, Adhi; Pranolo, Andri; Anwar, Nuril; Mao, Yingchi
       title: Parallel Approach of Adaptive Image Thresholding Algorithm on GPU
        date: 2022-03-05
       words: 7111
      flesch: 51
     summary: Researchers have been proposed parallel adaptive image thresholding methods for image segmentation. This paper is organized as follows: Section 2 presents the proposed approach of parallel adaptive image thresholding methods, Section 3 presents the result and discussion, and Section 4 presents the conclusion of this work. II.
    keywords: data; entropy; gpu; histogram; image; index; order; parallel; smem; sum; threshold
       cache: keds-25980.pdf
  plain text: keds-25980.txt

        item: #38 of 82
          id: keds-27765
      author: Suputra, Putu Hendra; Sensusiati, Anggraini Dwi; Artaria, Myrtati Dyah; Verkerke, Gijsbertus Jacob; Yuniarno, Eko Mulyanto; Purnama, I Ketut Eddy
       title: Automatic 3D Cranial Landmark Positioning based on Surface Curvature Feature using Machine Learning
        date: 2022-11-07
       words: 7094
      flesch: 56
     summary: Filter landmark prediction points by distance radius. The method uses VGG-net to draw the correlation of landmark positions based on a manually marked dataset.
    keywords: approach; cluster; curvature; data; feature; filter; landmark; learning; model; point; position; radius; scf; shape; surface
       cache: keds-27765.pdf
  plain text: keds-27765.txt

        item: #39 of 82
          id: keds-27938
      author: Mar'i, Farhanna; Ubaidillah, Hafidz; Mahmudy, Wayan Firdaus; Supianto, Ahmad Afif
       title: Hybrid Artificial Bee Colony and Improved Simulated Annealing for the Capacitated Vehicle Routing Problem
        date: 2022-12-30
       words: 6125
      flesch: 56
     summary: [23] Y. Deng, H. Xu, and J. Wu, “Optimization of blockchain investment portfolio under artificial bee colony algorithm,” J. Comput. [2] B. Yao, Q. Yan, M. Zhang, and Y. Yang, “Improved artificial bee colony algorithm for vehicle routing problem with time windows,” PLoS ONE 12 e0181275, pp.
    keywords: abc; algorithm; annealing; cvrp; dataset; distance; hybridization; optimization; problem; solution; table; vehicle; vol
       cache: keds-27938.pdf
  plain text: keds-27938.txt

        item: #40 of 82
          id: keds-28229
      author: Latumakulita, Luther Alexander; Lumintang, Sandy Laurentius; Salakia, Deiby Tineke; Sentinuwo, Steven R.; Sambul, Alwin Melkie; Islam, Noorul
       title: Human Facial Expressions Identification using Convolutional Neural Network with VGG16 Architecture
        date: 2022-06-07
       words: 4208
      flesch: 57
     summary: Human facial expression image data has been selected from open-source datasets (FER2013, JAFFE, and MUG). In addition, facial expression identification systems can be developed and applied in various fields, such as psychological patient emotion detection, lie detection, security system with face recognition, entertainment recommendations according to emotions (movies, music, tourist attractions, shopping products), robot development, monitoring system of an employee's facial expressions when interacting with Customers and so on.
    keywords: accuracy; confusion; data; expressions; fold; image; learning; matrix; model; table; training; vol
       cache: keds-28229.pdf
  plain text: keds-28229.txt

        item: #41 of 82
          id: keds-28311
      author: Sultan, Naveed
       title: Sentiment Analysis of Amazon Product Reviews using Supervised Machine Learning Techniques
        date: 2022-06-07
       words: 3668
      flesch: 57
     summary: Positive reviews predictions must lie between the range of 0.5 and less than 1 and false reviews ranges from 0 to 0.5 but from the figure below, some false prediction of positive reviews represented pessimistically, and some pessimistic predictions represented positive ones. Figure 1 is for positive reviews, and it is for negative reviews.
    keywords: accuracy; classification; data; ensemble; learning; machine; model; regression; reviews; tree; vol
       cache: keds-28311.pdf
  plain text: keds-28311.txt

        item: #42 of 82
          id: keds-29270
      author: Chuttur, Mohammad Yasser; Parianen, Yashinee
       title: A Comparison of Machine Learning Models to Prioritise Emails using Emotion Analysis for Customer Service Excellence
        date: 2022-11-07
       words: 6131
      flesch: 47
     summary: Our work contrasts with previous studies in that most works on email classification have focused on spam detection. In this study, we investigate the possibility of using machine learning to analyse the emotions expressed in emails to set a priority ranking to different emails.
    keywords: classification; dataset; email; emotions; engineering; knowledge; learning; machine; models; performance; priority; science; spam; training; vol
       cache: keds-29270.pdf
  plain text: keds-29270.txt

        item: #43 of 82
          id: keds-29489
      author: Pranolo, Andri; Mao, Yingchi; Wibawa, Aji Prasetya; Utama, Agung Bella Putra; Dwiyanto, Felix Andika
       title: Optimized Three Deep Learning Models Based-PSO Hyperparameters for Beijing PM2.5 Prediction
        date: 2022-11-07
       words: 6899
      flesch: 55
     summary: Using these functions, deep learning models can learn nonlinear prediction boundaries. The research reveals that the PSO optimized deep learning models (LSTM, CNN, and MLP) for Beijing PM2.5 multivariate time series prediction acquire a minimum error and improve its A. Pranolo et al. /
    keywords: cnn; data; forecasting; hyperparameter; layer; learning; lstm; mlp; model; network; neural; optimization; output; performance; prediction; pso; series; time; vol
       cache: keds-29489.pdf
  plain text: keds-29489.txt

        item: #44 of 82
          id: keds-29576
      author: Anshori, Mochammad; Haris, M. Syauqi
       title: Predicting Heart Disease using Logistic Regression
        date: 2022-12-30
       words: 5115
      flesch: 49
     summary: The findings of this study have significant implications for the field of heart disease prediction and can contribute to improved patient care and outcomes. These prior studies contribute to the understanding and development of machine learning approaches for heart disease prediction and classification.
    keywords: accuracy; data; disease; heart; machine; model; prediction; regression; value; vol
       cache: keds-29576.pdf
  plain text: keds-29576.txt

        item: #45 of 82
          id: keds-3148
      author: Septianto, Tri; Setyati, Endang; Santoso, Joan
       title: Digit Classification of Majapahit Relic Inscription using GLCM-SVM
        date: 2018-08-23
       words: 4161
      flesch: 59
     summary: [7] M. Mohamed Fathima, D. Manimegalai and S. Thaiyalnayaki, Automatic Detection of Tumor Subtype in Mammograms Based on GLCM and DWT Feature Using SVM, 2013 International Conference on Information Communication and Embedded Systems (ICICES), Chennai, 2013, pp. 809-813. Image classification is commonly used to create object recognition apps.
    keywords: classification; data; digit; features; fig; glcm; image; research; svm; year
       cache: keds-3148.pdf
  plain text: keds-3148.txt

        item: #46 of 82
          id: keds-36996
      author: Haviluddin, Haviluddin; Pakpahan, Herman Santoso; Puspitasari, Novianti; Putra, Gubtha Mahendra; Hasnida, Rima Yustika; Alfred, Rayner
       title: Adaptive Neuro-Fuzzy Inference System for Waste Prediction
        date: 2022-12-30
       words: 4074
      flesch: 53
     summary: One method that has shown promise in waste prediction is the Adaptive Neuro-Fuzzy Inference System (ANFIS). ANFIS has been successfully used in various applications, including waste prediction, because this method is adaptive, which means that if there is a change in parameter values, it will be connected to existing neurons in getting accurate prediction results
    keywords: anfis; data; forecasting; management; mape; model; prediction; results; samarinda; study; volume; waste
       cache: keds-36996.pdf
  plain text: keds-36996.txt

        item: #47 of 82
          id: keds-37102
      author: Manuaba, Ida Bagus Putra; Sentana, I Wayan Budi; Astawa, I Nyoman Gede Arya; Suasnawa, I Wayan; Pradnyana, I Putu Bagus Arya
       title: Social Media Mining with Fuzzy Text Matching: A Knowledge Extraction on Tourism After COVID-19 Pandemic
        date: 2022-12-30
       words: 3698
      flesch: 52
     summary: However, traditional text matching techniques, such as exact matching, are not always suitable for social media data, which can contain spelling mistakes, abbreviations, and variations in the use of words. The contribution of this research is to provide a better understanding of how COVID-19 recovery impacts the tourism industry and to demonstrate the potential of text mining and fuzzy matching techniques in extracting insights from social media data.
    keywords: covid-19; data; dataset; matching; media; mining; process; similarity; social; text; tourism; vol
       cache: keds-37102.pdf
  plain text: keds-37102.txt

        item: #48 of 82
          id: keds-37161
      author: Putri, Nastiti Susetyo Fanany; Wibawa, Aji Prasetya; Rosyid, Harits Ar; Utama, Agung Bella Putra; Uriu, Wako
       title: Performance of Ensemble Classification for Agricultural and Biological Science Journals with Scopus Index
        date: 2022-12-30
       words: 3419
      flesch: 55
     summary: Therefore, it is necessary to have data processing methods, such as classification. Where Bagging and Boosting comprise the ensemble, this research aims to evaluate the ensemble classification mechanism's performance using quartile data from agricultural and biological science periodicals.
    keywords: accuracy; adaboost; bagging; classification; data; ensemble; gnb; journal; method; vol; xgboost
       cache: keds-37161.pdf
  plain text: keds-37161.txt

        item: #49 of 82
          id: keds-37168
      author: Hechmi, Shili
       title: An Accurate Real-Time Method for Face Mask Detection using CNN and SVM
        date: 2022-12-30
       words: 5077
      flesch: 56
     summary: In this research, we suggest a real-time approach for face mask detection. Using a surgical mask is among the most significant safety precautions that can help keep this sort of pandemic from spreading, and manual monitoring of large crowds in public places for face masks is problematic.
    keywords: cnn; covid-19; data; detection; face; feature; image; mask; method; model; svm; technique
       cache: keds-37168.pdf
  plain text: keds-37168.txt

        item: #50 of 82
          id: keds-37229
      author: Asmara, Rosa Andrie; Noprianto, Noprianto; Ilmy, Muhammad Ainur; Arai, Kohei
       title: Traffic Density Prediction using IoT-based Double Exponential Smoothing
        date: 2022-12-30
       words: 4906
      flesch: 56
     summary: When smoothing time series data using an exponential function, the ARTICLE INFO A B S T R A C T Article history: Received 1 November 2022 Revised 7 December 2022 Accepted 11 December 2022 Published online 30 December 2022 It can be concluded that car vehicle detection is outnumbered by motorcycle detection.
    keywords: alpha; cascade; data; exponential; forecasting; haar; june; method; smoothing; system; time; traffic; vol; 𝑆𝑡 𝐼𝐼
       cache: keds-37229.pdf
  plain text: keds-37229.txt

        item: #51 of 82
          id: keds-37365
      author: Santoso, Joan; Setiawan, Esther Irawati; Ferdinandus, Fransiskus Xaverius; Gunawan, Gunawan; Hernandez, Leonel
       title: Indonesian Language Term Extraction using Multi-Task Neural Network
        date: 2022-12-30
       words: 4456
      flesch: 53
     summary: In recent years, joint models have become the algorithm used in many works. With the increasing use of joint models as an algorithm in specific tasks, we also proposed combining two neural network models to extract noun phrases from documents.
    keywords: extraction; indonesian; language; layer; model; neural; noun; phrase; pos; research; word
       cache: keds-37365.pdf
  plain text: keds-37365.txt

        item: #52 of 82
          id: keds-37407
      author: Ar Rosyid, Harits; Putra, Aulia Yahya Harindra; Akbar, Muhammad Iqbal; Dwiyanto, Felix Andika
       title: Can Multinomial Logistic Regression Predicts Research Group using Text Input?
        date: 2022-12-30
       words: 4663
      flesch: 57
     summary: With performances just above 63% in overall metrics, we argue that this MLR model with title text input is optimal due to its small dimensionality. Based on the experiments, research group classification using title-only input is the best overall.
    keywords: abstract; classification; data; engineering; figure; group; mlr; research; results; scenario; science; text; title
       cache: keds-37407.pdf
  plain text: keds-37407.txt

        item: #53 of 82
          id: keds-37459
      author: Alzuhdi, Akmal Vrisna; Ar Rosyid, Harits; Chuttur, Mohammad Yasser; Nazir, Shah
       title: Optimizing Random Forest Algorithm to Classify Player's Memorisation via In-game Data
        date: 2023-10-02
       words: 5857
      flesch: 50
     summary: Serious game players are more empowered to become more actively involved, not only in the learning process but also in the design and development of cutting-edge formative assessment tools, as discussed by Hainey et al., and serious games are becoming more and more popular as alternative supplementary learning approaches across all disciplines at all levels [23]. A B S T R A C T Article history: Received 13 April 2023 Revised 30 August 2023 Accepted 25 September 2023 Published online 4 October 2023 Assessment of a player's knowledge in game education has been around for some time.
    keywords: classifiers; data; dataset; forest; game; gscv; knowledge; learning; memorization; n_estimators; player; research; vol
       cache: keds-37459.pdf
  plain text: keds-37459.txt

        item: #54 of 82
          id: keds-38346
      author: Prasetya, Didik Dwi; Hirashima, Tsukasa
       title: Associated Patterns in Open-Ended Concept Maps within E-Learning
        date: 2022-12-30
       words: 5330
      flesch: 47
     summary: Although several studies on mining concept maps have been carried out, only a few have analyzed the knowledge structure. It has been demonstrated that concept maps are beneficial for instruction, learning, and evaluation
    keywords: analysis; association; concept; data; knowledge; maps; mining; rules; support; table; term; vol
       cache: keds-38346.pdf
  plain text: keds-38346.txt

        item: #55 of 82
          id: keds-38745
      author: Wibawanto, Slamet; Kirana, Kartika Candra; Ramadhan, Hani
       title: Ant Colony Optimization for Resistor Color Code Detection
        date: 2023-06-06
       words: 4283
      flesch: 48
     summary: Many combinations of color bands raise the need for technology that can automatically measure resistor values visually. The test data is crucial for assessing the generalization capabilities of the proposed method and its ability to accurately estimate resistor values in real-world settings.
    keywords: ant; ants; colony; color; data; information; optimization; pheromone; resistor; ring; solutions; values
       cache: keds-38745.pdf
  plain text: keds-38745.txt

        item: #56 of 82
          id: keds-3976
      author: Darusalam, Darusalam; Ashman, Helen
       title: Profiling and Identifying Individual Users by Their Command Line Usage and Writing Style
        date: 2018-08-23
       words: 4662
      flesch: 53
     summary: To evaluate this particular characteristic this research will use the n-gram analysis method, and will aim to identify users in two ways, positive user identification and negative user identification. This research will perform the same analysis on data of both types, using exactly the same analysis, and will determine firstly whether either form can be used successfully for user identification, and if so, the research will then determine which is the more effective of the two.
    keywords: gram; identification; language; normalization; percentage; research; samples; test; user
       cache: keds-3976.pdf
  plain text: keds-3976.txt

        item: #57 of 82
          id: keds-40159
      author: Iddrisu, Issah; Appiahene, Peter; Appiah, Obed; Fuseini, Inusah
       title: Exploring the Impact of Students Demographic Attributes on Performance Prediction through Binary Classification in the KDP Model
        date: 2023-06-25
       words: 9250
      flesch: 46
     summary: Three different ML technique was used to forecast student performance [18]. The research findings suggest that using ML to anticipate student performance may be helpful.
    keywords: algorithms; attributes; classification; data; demographic; education; information; intervention; knowledge; learning; machine; mining; model; performance; prediction; science; students; study; vol
       cache: keds-40159.pdf
  plain text: keds-40159.txt

        item: #58 of 82
          id: keds-40180
      author: Walid, Miftahul; Sahbaniya, Norfiah Lailatin Nispi; Hozairi, Hozairi; Baskoro, Fajar; Wijaya, Arya Yudhi
       title: K-Means Clustering and Multilayer Perceptron for Categorizing Student Business Groups
        date: 2023-09-18
       words: 4506
      flesch: 52
     summary: The distribution of the data used in this research based on topic data can be seen in Figure 2. [34] M. H. Santoso, D. A. Larasati, U. Medan, and A. Sumatera, Wayang Image Classification Using MLP Method and GLCM Feature Extraction, J. Comput.
    keywords: classification; clustering; data; learning; means; mlp; model; multilayer; process; results; topic; transaction; vol
       cache: keds-40180.pdf
  plain text: keds-40180.txt

        item: #59 of 82
          id: keds-40357
      author: Gunawan, Gunawan; Fitria, Fitria; Setiawan, Esther Irawati; Fujisawa, Kimiya
       title: Maximum Marginal Relevance and Vector Space Model for Summarizing Students' Final Project Abstracts
        date: 2023-08-01
       words: 6292
      flesch: 45
     summary: WHILE (row is not empty) 34: document ← GET field document 35: last ← GET field last 36: ENDWHILE 37: WRITE file summary SET field document= document, \ field last=last 38: delete file cosine where field document=document 39: drop file mmr 40: create table mmr has fields document, last 41: READ all fields from summary 42: The steps in this research will start with the user selecting or searching for text documents that will be summarized with keywords in the abstract as a query.
    keywords: cosine; data; document; field; mmr; query; relevance; results; sentence; similarity; summarization; summary; table; text; value; weight
       cache: keds-40357.pdf
  plain text: keds-40357.txt

        item: #60 of 82
          id: keds-40397
      author: Gultom, Zuli Agustina; Siregar, Farid Akbar; Tanjung, Mahardika Abdi Prawira; Hazidar, Al-Hamidy
       title: Multivariate Analysis Approach to Factor-Affected Tuberculosis Disease
        date: 2023-10-03
       words: 6233
      flesch: 45
     summary: So that discriminant analysis can be used for predicting the accuracy of tuberculosis prevalence rates. The goal of this research is to find out what factors influence the prevalence rate of tuberculosis in the city of Surabaya and to group regions based on the characteristics of the incidence of tuberculosis, with the hope that this research can help the Surabaya city government in handling tuberculosis prevalence rates quickly and accurately The analysis technique used is multivariate analysis.
    keywords: analysis; data; education; facilities; factor; group; health; number; rate; sub; surabaya; tuberculosis; variable; vol
       cache: keds-40397.pdf
  plain text: keds-40397.txt

        item: #61 of 82
          id: keds-40889
      author: Kurniawati, Arik; Yuniarno, Eko Mulyanto; Suprapto, Yoyon Kusnendar
       title: Deep Learning for Multi-Structured Javanese Gamelan Note Generator
        date: 2023-07-18
       words: 8227
      flesch: 48
     summary: The input data of this study consists of balungan notation, rhythm type, song structure type, and gatra information, while the output data consists of ricikan struktural music notation such as kenong, kethuk, kempyang, kempul, gong ageng, and gong suwuk. A. Kurniawati et al. / Knowledge Engineering and Data Science 2023, 6 (1): 41–56 48 To provide a comparative analysis, we compared the performance of the CNN-LSTM model with that of the CNN and LSTM models.
    keywords: cnn; data; gamelan; gatra; gong; instruments; kempul; lstm; model; music; notation; note; ricikan; song; structure; struktural; study; tanggung; training
       cache: keds-40889.pdf
  plain text: keds-40889.txt

        item: #62 of 82
          id: keds-42537
      author: Armanda, Tubagus Arief; Wardhani, Ire Puspa; Akhriza, Tubagus M.; Admira, Tubagus M. Adrie
       title: Recurrent Session Approach to Generative Association Rule based Recommendation
        date: 2023-11-02
       words: 8797
      flesch: 56
     summary: Consequently, AR-based RS provides a variety of item recommendations. K recommendation items obtained E. Benchmarking the Model The activity flow of benchmarking the model is given in Figure 8, which shows that the proposed model is compared with the query-based session method.
    keywords: accuracy; data; items; method; model; recommendation; results; rules; science; series; session; training; user; vol
       cache: keds-42537.pdf
  plain text: keds-42537.txt

        item: #63 of 82
          id: keds-43667
      author: Sudiatmika, I Kadek Wahyu; Indrawan, Gede; Sariyasa, Sariyasa
       title: Round-Robin Algorithm in Load Balancing for National Data Centers
        date: 2023-09-22
       words: 6531
      flesch: 42
     summary: [28] M. Elveny, A. Winata, B. Siregar, and R. Syah, “A Tutorial: Load Balancers in a Container technology System using Docker Swarms on a Single Board Computer Cluster,” Ilkogr. In the context of load testing, our objective is to accurately simulate the dynamic patterns of user interactions with the load balancer through a meticulously constructed average-load testing scenario.
    keywords: algorithm; balancer; balancing; bali; data; government; knowledge; load; load balancer; min=0s; performance; robin; round; server; system; testing; vol
       cache: keds-43667.pdf
  plain text: keds-43667.txt

        item: #64 of 82
          id: keds-44603
      author: Karim, Atkia Akila; Nower, Naushin
       title: Long-Term Traffic Prediction Based on Stacked GCN Model
        date: 2023-09-24
       words: 5944
      flesch: 51
     summary: Numerous specialists and academics have dedicated their research to studying traffic flow prediction and have developed numerous prediction ARTICLE INFO Keywords: Traffic flow prediction Long-term prediction Graph Convolutional Network Segment http://u.lipi.go.id/1502081730 http://u.lipi.go.id/1502081046 http://journal2.um.ac.id/index.php/keds mailto:keds.journal@um.ac.id https://creativecommons.org/licenses/by-sa/4.0/ https://creativecommons.org/licenses/by-sa/4.0/ 93 Karim et al. /
    keywords: data; flow; gcn; graph; learning; model; network; prediction; road; segments; term; time; traffic; traffic flow; vol
       cache: keds-44603.pdf
  plain text: keds-44603.txt

        item: #65 of 82
          id: keds-44851
      author: Sujatna, Yayat; Karno, Adhitio Satyo Bayangkari; Hastomo, Widi; Yuningsih, Nia; Arif, Dody; Handayani, Sri Setya; Kardian, Aqwam Rosadi; Wardhani, Ire Puspa; Rere, L.M Rasdi
       title: Stacked LSTM-GRU Long-Term Forecasting Model for Indonesian Islamic Banks
        date: 2023-11-06
       words: 8952
      flesch: 56
     summary: [54] J. Brownlee, “How to develop LSTM models for time series forecasting (2018).” The traditional LSTM and GRU models have several limitations compared to model stacks that combine LSTM and GRU.
    keywords: data; days; g l; gru; indonesia; islamic; learning; lstm; model; mse; prediction; price; stock; term; test; time; training; vol; 𝐿𝑆𝑇𝑀𝑖
       cache: keds-44851.pdf
  plain text: keds-44851.txt

        item: #66 of 82
          id: keds-44877
      author: Admojo, Fadhila Tangguh; Lajis, Adidah; Nasir, Haidawati
       title: Systematic Literature Review on Ontology-based Indonesian Question Answering System
        date: 2023-10-03
       words: 9770
      flesch: 36
     summary: This literature review paper delves into the state of ontology- based Indonesian QA systems, highlighting critical challenges. Knowledge Engineering and Data Science 2023, 6 (2): 129–144 140 Exploring more sophisticated query generation techniques for future advancements in ontology- based Indonesian QA systems is necessary.
    keywords: analysis; answering; challenges; data; domain; indonesian; indonesian qa; information; knowledge; language; linguistic; ontology; qa system; query; question; review; semantic; sentence; sparql; system; vol
       cache: keds-44877.pdf
  plain text: keds-44877.txt

        item: #67 of 82
          id: keds-45009
      author: Hanif, Benzfica; Larasati, Aisyah; Nurdiansyah, Rudi; Le, Trung
       title: The Effect of the Number of Hidden Layers on The Performance of Deep Q-Network for Traveling Salesman Problem
        date: 2023-10-04
       words: 5256
      flesch: 43
     summary: Loss value using different level parameter Parameter Loss Episode Epoch 50 1 7.005321025848389 Figure 3 and Figure 4 provide aesthetically captivating representations of the research outcomes, revealing intricate patterns in the dynamics of loss values.
    keywords: data; dqn; episode; epochs; knowledge; layers; learning; loss; model; network; number; research; study; value
       cache: keds-45009.pdf
  plain text: keds-45009.txt

        item: #68 of 82
          id: keds-46417
      author: Ojugoa, Arnold Adimabua; Odiakaose, Christopher Chukwufunaya; Emordi, Frances; Ako, Rita Erhovwo; Adigwe, Winifred; Anazia, Kizito Eluemonor; Geteloma, Victor
       title: Evidence of Students’ Academic Performance at the Federal College of Education Asaba Nigeria: Mining Education Data
        date: 2023-10-11
       words: 7777
      flesch: 56
     summary: [2] M. I. Akazue, R. E. Yoro, B. O. Malasowe, O. Nwankwo, and A. A. Ojugo, “Improved services traceability and management of a food value chain using block-chain network : a case of Nigeria,” Indones. [4] R. E. Yoro, F. O. Aghware, B. O. Malasowe, O. Nwankwo, and A. A. Ojugo, “Assessing contributor features to phishing susceptibility amongst students of petroleum resources varsity in Nigeria,” Int.
    keywords: a. a.; a. ojugo; classification; credit; data; decision; distinction; education; gain; int; knowledge; learning; merit; mining; ojugo; performance; student; tree; vol
       cache: keds-46417.pdf
  plain text: keds-46417.txt

        item: #69 of 82
          id: keds-46553
      author: Sumarti, Heni; Septiani, Fahira; Sudarmanto, Agus; Caesarendra, Wahyu; Edison, Rizki Edmi
       title: EEG Classification while Listening to Murottal Al-Quran and Classical Music using Random Forest Method
        date: 2023-10-18
       words: 6958
      flesch: 54
     summary: Brain signal data is extracted in EDF form, then processed using brain wave data for 1 minute, selected based on the best signal (with no/little noise and artifacts) separated using the EDF browser. Brain signal data is stored as an edf file, then separated using the edf browser to get brain signals for one minute.
    keywords: alpha; beta; brain; classification; data; delta; forest; method; murottal; music; quran; research; stimulation; theta; vol; waves
       cache: keds-46553.pdf
  plain text: keds-46553.txt

        item: #70 of 82
          id: keds-46800
      author: Wibawa, Aji Prasetya; Utama, Agung Bella Putra; Akbari, Ade Kurnia Ganesh; Fadhilla, Akhmad Fanny; Triono, Alfiansyah Putra Pertama; Paramarta, Andien Khansa’a Iffat; Setyaputri, Faradini Usha; Hernandez, Leonel
       title: Deep Learning Approaches with Optimum Alpha for Energy Usage Forecasting
        date: 2023-10-17
       words: 7813
      flesch: 48
     summary: They can automatically extract essential features from time series data, such as seasonal patterns, trends, cycles, and irregularities. [14] can directly process time series data without the need for image conversion.
    keywords: alpha; data; energy; engineering; forecasting; lstm; model; series; smoothing; time; usage; value; vol; wibawa
       cache: keds-46800.pdf
  plain text: keds-46800.txt

        item: #71 of 82
          id: keds-47329
      author: Riza, Lala Septem; Rahman, M Ammar Fadhlur; Prasetyo, Yudi; Zain, Muhammad Iqbal; Siregar, Herbert; Hidayat, Topik; Samah, Khyrina Airin Fariza Abu; Rosyda, Miftahurrahma
       title: Comparison of Machine Learning Algorithms for Species Family Classification using DNA Barcode
        date: 2023-11-06
       words: 8382
      flesch: 48
     summary: The data used are DNA barcode sequence data obtained from GenBank [52] (ncbi.nlm.nih.gov, accessed August 15, 2023). Figure 5 shows an example of DNA sequence data before and after sequence alignment.
    keywords: allium; amaryllidaceae; art; barcode; classification; data; dataset; dna; family; learning; liliaceae; machine; model; riza; science; sequence; species; training; vol
       cache: keds-47329.pdf
  plain text: keds-47329.txt

        item: #72 of 82
          id: keds-4797
      author: Hernandez, Leonel; Jimenez, Genett; Marchena, Piedad
       title: Energy Efficiency Metrics of University Data Centers
        date: 2018-08-23
       words: 5241
      flesch: 56
     summary: As Baccour says [1], data centers use the network between 5 % and 25 %, and therefore the energy consumed by inactive devices is wasted. Data centers, composed of many servers, can absorb as much power as a small city, in fact, numerous studies have shown that average server utilization is usually less than 30% of maximum utilization [2].
    keywords: campus; center; consumption; data; data center; efficiency; energy; switch; total
       cache: keds-4797.pdf
  plain text: keds-4797.txt

        item: #73 of 82
          id: keds-4798
      author: Ismail, Amelia Ritahani; Ali, Nur ‘Atikah Binti Mohd; Sulaiman, Junaida
       title: Change Vulnerability Forecasting Using Deep Learning Algorithm for Southeast Asia
        date: 2018-08-23
       words: 2377
      flesch: 51
     summary: This study uses machine learning approach to predict of climate change vulnerability in South East Asia. This operator transforms a given example set containing series data into a new example set which contains single valued examples4.
    keywords: change; climate; data; index; learning; readiness; vulnerability
       cache: keds-4798.pdf
  plain text: keds-4798.txt

        item: #74 of 82
          id: keds-5804
      author: Darusalam, Darusalam; Said, Jamaliah; Omar, Normah; Janssen, Marijn; Sohag, Kazi
       title: The Diffusion of ICT for Corruption Detection in Open Government Data
        date: 2019-06-23
       words: 5874
      flesch: 44
     summary: The following section of this research provides background information regarding the developments including open government data (OGD), data-driven detection of corruption and overview of stakeholder. The determined critical concepts for the literature reviews include open government data, corruption, and accountability.
    keywords: architecture; corruption; data; government; ict; information; open; public; reference; research; system; vol
       cache: keds-5804.pdf
  plain text: keds-5804.txt

        item: #75 of 82
          id: keds-5832
      author: Hozairi, Hozairi; Buhari, Buhari; Lumaksono, Heru; Tukan, Marcus
       title: Selection of Marine Security Policy using Fuzzy-AHP TOPSIS Hybrid Approach
        date: 2019-06-23
       words: 5145
      flesch: 67
     summary: The finding shows that the hybrid approach is able to produce the best recommendation for Indonesian maritime security policy. Hierarchy of selection of Indonesian maritime security policies Table 3.
    keywords: ahp; criteria; decision; fuzzy; maritime; policy; security; table; topsis; value; 𝑉(𝑀
       cache: keds-5832.pdf
  plain text: keds-5832.txt

        item: #76 of 82
          id: keds-6058
      author: Anissa, Retno Dewi; Mahmudy, Wayan Firdaus; Widodo, Agus Wahyu
       title: Optimisation of Rice Fertiliser Composition using Genetic Algorithms
        date: 2019-12-23
       words: 4123
      flesch: 58
     summary: There are nine chromosomes formed, five initial chromosomes are used to calculate the amount of fertilizer, content, total price needed and fitness value. Fitness values can be expressed in (1).
    keywords: algorithm; crossover; fertiliser; fitness; generation; mutation; population; rate; size; value
       cache: keds-6058.pdf
  plain text: keds-6058.txt

        item: #77 of 82
          id: keds-6530
      author: Febrita, Ruth Ema; Mahmudy, Wayan Firdaus; Wibawa, Aji Prasetya
       title: High Dimensional Data Clustering using Self-Organized Map
        date: 2019-06-23
       words: 5681
      flesch: 65
     summary: This research implements the Self-Organized Map (SOM) algorithm to cluster house data for providing several house groups based on the various features. SOM cluster and label the transient data by checking the similarity of the pattern.
    keywords: cluster; clustering; coefficient; data; house; map; means; neuron; number; silhouette; som; value
       cache: keds-6530.pdf
  plain text: keds-6530.txt

        item: #78 of 82
          id: keds-6775
      author: Jais, Imran Khan Mohd; Ismail, Amelia Ritahani; Nisa, Syed Qamrun
       title: Adam Optimization Algorithm for Wide and Deep Neural Network
        date: 2019-06-23
       words: 2336
      flesch: 58
     summary: On the other hand, [1] investigate on how wide linear models can effectively memorize sparse feature interactions using cross-product feature transformations, while deep neural networks can simplify to formerly unseen feature interactions through low dimensional embeddings. D. Machine Learning The wide and deep neural network requires the user to define which features are base features, crossed features, and deep features.
    keywords: adam; data; features; learning; network; neural; optimization
       cache: keds-6775.pdf
  plain text: keds-6775.txt

        item: #79 of 82
          id: keds-6935
      author: Azhari, Ahmad; Susanto, Adhi; Pranolo, Andri; Mao, Yingchi
       title: Neural Network Classification of Brainwave Alpha Signals in Cognitive Activities
        date: 2019-12-23
       words: 4711
      flesch: 59
     summary: The application of EEG signals in the biomedical field is the development of bio-signal processing. EEG signals are an essential source used to study, monitor, and evaluate the activity of the human brain.
    keywords: brain; cognitive; data; eeg; feature; process; results; signals; stimulus; subject; task
       cache: keds-6935.pdf
  plain text: keds-6935.txt

        item: #80 of 82
          id: keds-7335
      author: Aini, Hijratul; Haviluddin, Haviluddin
       title: Crude Palm Oil Prediction Based on Backpropagation Neural Network Approach
        date: 2019-06-23
       words: 3479
      flesch: 66
     summary: ∆𝑣𝑖𝑗𝑗 = 𝛼𝛿𝑗𝑥𝑖 (10) where, ∆𝑣ij is neuron input weight to neuron hidden, 𝛼 is learning rate, 𝛿j is weight correction factor vij, 𝑥i is neuron input i C. Update weight and bias steps 𝑍_𝑖𝑛 = 𝑣 + ∑ 𝑥𝑖 𝑖 𝑛=1 𝑣𝑖𝑗 (1) where Z is neuron hidden, 𝑣 is input bias weight neuron to j, 𝑥 is neuron input i, 𝑣 is neuron input to neuron hidden weights.
    keywords: bpnn; data; input; layer; learning; neuron; output; prediction; weight
       cache: keds-7335.pdf
  plain text: keds-7335.txt

        item: #81 of 82
          id: keds-7803
      author: Pujianto, Utomo; Setiawan, Asa Luki; Rosyid, Harits Ar; Salah, Ali M. Mohammad
       title: Comparison of Naïve Bayes Algorithm and Decision Tree C4.5 for Hospital Readmission Diabetes Patients using HbA1c Measurement
        date: 2019-12-23
       words: 8097
      flesch: 55
     summary: The second scenario in this study applies the SMOTE method for minority class data so that the distribution of label classes is balanced, moreover the number of label classes consists of the same three classes with scenario one. The concept of data cleaning applied in this study is by removing attribute values that have very high missing values such as the attribute payer code with a missing value of 52 % which has the potential to have no correlation with this study, and the weight and Medical specialty attribute that should be removed because it has very large missing values.
    keywords: accuracy; algorithm; attributes; bayes; c4.5; classes; classification; data; feature; method; naïve; number; patients; results; scenario; selection; smote; value
       cache: keds-7803.pdf
  plain text: keds-7803.txt

        item: #82 of 82
          id: keds-9869
      author: Haviluddin, Haviluddin; Alfred, Rayner; Moham, Ni’mah; Pakpahan, Herman Santoso; Islamiyah, Islamiyah; Setyadi, Hario Jati
       title: Handwriting Character Recognition using Vector Quantization Technique
        date: 2019-12-23
       words: 4236
      flesch: 61
     summary: Image processing processes signal which input is an image. Materials and Methods This part briefly discusses Buginese Lontara script pattern, LVQ method, and image processing employed in this research.
    keywords: data; feature; image; layer; learning; lontara; lvq; process; processing; recognition; script
       cache: keds-9869.pdf
  plain text: keds-9869.txt