INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL Online ISSN 1841-9844, ISSN-L 1841-9836, Volume: 16, Issue: 5, Month: Octobre, Year: 2021 Article Number: 4239, https://doi.org/10.15837/ijccc.2021.5.4239 CCC Publications Role of Modern Technologies and Internet of Things in the Field of Solid Waste Management S.Godwin Barnabas, K.A.V. Geethan, S.Valai Ganesh, S.Rajakarunakaran, P.Sabarish Kumar S.Godwin Barnabas*, S.Valai Ganesh and S.Rajakarunakaran Department of Mechanical Engineering Ramco Institute of Technology Rajapalayam 626117, Tamil Nadu, India *Corresponding author: godwin@ritrjpm.ac.in valaiganesh@ritrjpm.ac.in rajakarunakaran@ritrjpm.ac.in K.Arun vasantha Geethan, P.Sabarish Kumar Department of Mechanical Engineering St. Joseph’s Institute of Technology Chennai 600119, Tamil Nadu, India kavgeeth@gmail.com pskgps@gmail.com Abstract The process of handling solid waste becomes complex and tedious due to the urbanization and industrialization of the most developing and developed countries. These solid waste issues if it is not addressed properly it affects ecosystem and environment. There is a possibility of many health-oriented issues especially during the pandemic period covid-19. Most of the human beings are struggling with respiratory pulmonary diseases, asthma caused by these solid wastes. Most of the governments are also spending huge amount of money for labors, devices and some technologies to tackle these solid waste issues. There is also an opportunity for the government to generate revenue from these solid wastes by properly sorting these waste into recyclable, non- recyclable and bio-degradable wastes. But when humans are involved in sorting these waste it will cause some diseases and hygienic problems. So,in order to address the above said issues in this work the role of modern technologies, algorithms and some Internet of things (IoT) methods are discussed. Implementing these technologies in the future will save huge amount of money spent by the government for the solid waste management activities. Keywords: environment, pandemic period, diseases, technologies, internet of things. 1 Introduction The recent survey conducted by the world bank predicts that solid waste generation would rise up to 2.3 billion by 2025. Waste management is serious problem to both the developed and developing https://doi.org/10.15837/ijccc.2021.5.4239 2 nation. Improper waste management will lead to much health-related breathing diseases like asthma and Chronic Obstructive Pulmonary Disease. People who are residing near the garbage area will be affected by dengue, viral fever and other fatal diseases. More than 230 million people become the victim for inhalation problems due to air pollution. The proper waste management just assures the health of the aspirants residing near the garbage. But most of the waste which are landfilled will affect the ecosystem and it becomes a big threat to the environment and cultivation. In India there is no cost-effective waste segregated approach at each individual house which is the high demand at this time for effective waste management. Industries are planning for zero waste goal but they are able to reduce only 70% of the waste collected. If the plastics are properly recycled instead of landfilling 60 Tonnes of oil barrel could be produced. This paper reviews two major waste management system in house hold; one is biological method and other one is physiochemical method. Also, they conclude that waste management for domestic use will reduce the amount of solid waste for transportation and collection work [23] but there are some barriers in handling the recycling activities 1) laws and regulations framed by the government and budget allocated for recycling activities. 2) most of the peoples are unaware of the self-recycling. 3) There is no proper recycling technology 4) Expenses in waste management[20]. In order to address this issue, it is necessary to sort these wastes into recyclable, non-recyclable and bio-degradable wastes. which will include all the solid wastes ranging from paper, plastic, rubber, sheet metal, glass etc., there are two types of possible errors in sorting one is not identifying the correct object and the second one is placing one category over the other. also sorting by the humans are non-hygienic so some robots with picking arm and artificial intelligence concepts are used for sorting the wastes.Revenue generation by sorting the recyclable waste will increase through artificial intelligence and automation methods. When the automation is combined with recycling work with the back support of artificial intelligence recycling task gets smarter day to day. 2 Role of IoT,Modern technologies, optimization techniques, and of Radio Frequency Identification (RFID) in solid waste manage- ment This paper discusses about the following; 1. Part of IoT in in solid waste management 2. Part of modern technologies 3. Use of optimization techniques and algorithms 4. Part of Radio Frequency Identification (RFID) in solid waste management 2.1 Part of IoT in in solid waste management Reduction of waste by adopting modern industrial automation techniques in waste management was carried out. To improve performance of the solid waste management process there are various technologies like artificial intelligence, IoT (internet of things), automation, were well planned and implemented. The objective here is to combining the smart cities with the aid of IoT, collecting data and analyzing the data using Big Data, Data Analytics concepts. By this modern technology introduction, waste processing of any part of the geographical area could be assessed easily. When the trash is coupled with IoT used to identify the trash volume by the servers. Data collected in the waste management is given as input for the Graph theory optimization and other related algorithms combined to form efficient waste management system [16]. Sensors are used to identify the trash volume which helps to prevent the overflow of trash bins. Once the sensors give the signal of trash overflow level it will be cleaned immediately on the routine basis. For that the sensors are equipped with low weight operating systems called Contiki and TinyOS.The main objective here is the cloud of sensors and actuators are used as a service providers for data filtering for the efficient smart city management system [39]. Some of the recycling industries are using the robots to sort out the recyclable and recyclable waste. In this paper some modern tools, technologies, economical and hygienic artificial intelligence methods https://doi.org/10.15837/ijccc.2021.5.4239 3 for picking the garbage are discussed to address the waste management issues in many countries. In this work, the role of IoT is to separate the dry waste and wet waste with the aid of modern control system. In conveyor belt the dry waste is collected in the dust bin on one half portion of the bely and the wet waste is collected in the bins on the another side. Here IoT is used as a medium to control and monitor the waste for a single man and organization.By this effort they to develop all the rural and urban regions of the world [8].In this work the design for data sharing was made possible truck driver on time for the waste collection and the optimized route for garbage clearance by using the method called intelligent transportation system. This has been possible with the help of IoT components like RFID sensors, vision systems, controllers and surveillance systems to monitor the problematic areas in the waste collection and that supports the authorities [3]. This work includes design, implementation, and evaluation of IoT technology for the waste management in restaurants at Suzhou, China. The objectives are collecting, transportation and final disposal of the restaurant food waste. The developed IoT architecture with hardware and software to address the huge restaurant food waste yields fruitful results [60]. Here the waste management is automated with the help of IoT by gathering the garbage level through the webpage. For this; android application is merged with web server from the webpage the information will be sent to waste collecting vehicle and the officials. This smart garbage bin is considered to be the innovative method in waste management to make a clean environment. By this smart garbage system the overflow of wastes in public areas were avoided to prevent the common peo- ples from diseases[27]. Inefficient waste management will lead to environmental hazards and increase cost in waste management activities. Here smart garbage bin (SGB) has been implemented with IoT for the convenience of the users for information sharing of garbage through wireless network and it increases the battery life of SGB. This SGB have been used in the Gangnam district, Seoul, Republic of Korea, for the period 12 months. The report shows that waste of food were considerably reduced by 33%. They have developed the SGB in two modes 1. Standalone operation 2.cooperation based operation [21]. This work comprises of two studies one is related to the solid waste collection issues. The second study is about the IoT enabled kanban system is planned for waste management. The purpose of including the kanban is for the mean to sgnal time and quantity of waste collection.Due to this kannban system large volume of solid waste collection in the different geographical region is possible [57]. The overflow of garbage system will create unhygienic scenarios and it will affect the environment. To prevent this many concepts of effective smart garbage management system coupled with IoT is discussed but, each method has its own pros and cons.Here the smart garbage management system with, IoT, micro-controller, and Wi-Fi is used in many cities [24]. Three-layered architecture for IoT real time solid waste monitoring was designed in this work. The lower layer is equipped with input devices like sensors to sense the waste level in the bin. The second layer also called as middle layer includes wi-fi and GSM technologies is used for transmission of collected data from lower layer to the central system. Finally, the upper layer consist of cloud service for storing and receiving the data from the sensors. This device is designed with an objective to create a green environment. This system uses wireless sensor networks and different communication technologies to monitor the status of solid waste [11]. The routing issues in waste management issues is addressed by IoT enabled waste management. They implemented the smart cities with the distribution of waste trucks and waste bins are equipped with modern sensors and actuators with IoT enhancement to address the routing issues in waste management. Apart from the scheduling and routing issues this work focuses on stochastic reassign of trucks to collect the wastes generated [56]. This work discusses the necessity of new smart waste management system to improve the quality of life of the people. This is achieved by the use of internet of things (IoT) for smart recycling. This model includes dumpster with sensor, then this model is compared with present technologies for future scope of action [36]. Here the new type of technology called dynamic waste management model specially supported with IoT, sensors, actuators and radio frequency (RFID) for process monitoring and collecting of wastes in smart cities is developed. There are three phases in this model 1) waste collection planning and execution with the proper solution by restricting to the some locations. 2) Transportation of the waste depends on the type of waste 3) reusing the recycled waste. This work yields better results and provides excellence https://doi.org/10.15837/ijccc.2021.5.4239 4 in waste management. Analyzed the strengths and weakness of various models of IoT enabled waste management system [5]. 2.2 Role of modern technologies The automatic garbage collection system by introducing intelligence artificially to work as a garbage collecting robot. This robot act like an alternative compound to handle the waste management issues in the places especially in hospitals, theatres, supermarkets, grounds and many parks. The system function in which it uses the sensors to detect the garbage level, the volume of garbage generated and stored as database. This database is further sent to the servers. The data which is gathered is processed for cleaning the garbage collected. This method proves to be economical in comparison to the cost saved in transportation, human labors wages and finally it is a time saving process. The main components of the system function are microcontroller, sensors, battery output, and artificial intelligence. From the data collected the possibility of trash filling is calculated by statistical methods and based trash filling priority the trash will be cleaned for various locations in the country [45].Smart dust bin is the other concept it is assembled with piston arrangement which is used for the compression of garbage. This device is essential for the garbage overflow due to errors happening in the cleaning team [50]. The use of ICT (Information and Communication Technology) becomes necessary for the mod- ern waste management it includes data acquisition technologies, spatial technologies, identification technologies, and data communication technologies. Which is necessary for planning, monitoring, collecting and managing the collected solid waste. This work reviews the fundamentals of ICT and their application in the solid waste management for planning and design of the new system[19]. Sup- port vector machine (SVM), adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN) and k-nearest neighbors (kNN) are used for handling the waste. These four machine learn- ing models provides better prediction of solid waste generation. These algorithms used to provide forecasting accuracy of waste generation in Queensland, Australia. Regression analysis, descriptive statistical models, time series analysis and deep learning models are the four different methods used to calculate the solid waste generation for the upcoming years. The result shows that machine learning algorithms shows good result in predicting the waste. Adaptive neuro-fuzzy inference system (ANFIS) were used to forecast the waste generation in the Logan city with the aid of time series. The results of ANFIS is compared with SVM (support vector machine) and KNN (K nearest-neighbor) models to find the best machine learning model to be introduce in future [37]. ANN (artificial neural network) have been used to calculate the solid waste generation in Mashhad city with the aid of time series dataset of waste generation. To compare the accuracy of forecasting regression results are compared with ANN. From this work the prediction for the solid waste generation for the year 2032 was made with ANN and it found to be the best results [40]. Most accurate model for the prediction of solid waste generation and diversion for more than 200 municipalities in province of Ontario, Canada .Two machine learning algorithms such as artificial neural network and decision tree models were used to predict the exact waste generation and diversion details based on the socio- economic and demographic criterias [25]. Used artificial neural network (ANN) to forecast the waste generation in Bangkok city. It doesn’t yield better results because of large and noisy data.so it is needed to be processed with wavelet method. Developed the time series model and other suitable model for solid waste generation. ANN model is trained with back propagation algorithm [52]. Discrete wavelet transform and artificial neural network (ANN) is used for forecasting involving uncertainties in supply chain logistics. Discrete wavelet transform and (ANN) produce less bullwhip effect compared to Autoregressive Integrated Moving Average (ARIMA) model. Deep Neural Network models have been used to predict the data in various fields such as hydrology, supply chain demand forecasting, electricity price and load forecasting, flood forecasting. It is used in predicting waste generated by using time series dataset in Delhi from 1993-2011[21, 49]. This work presents the concept of smart management system for handling waste by using wireless sensor network and embedded system to collect the waste information. This device informs the authorities based on the information gathered to carry out this task wireless sensor network and embedded linux board . Linux board normally used here is Raspberry Pi [28]. https://doi.org/10.15837/ijccc.2021.5.4239 5 Here the system is simulated from the waste data’s collected in city of Copenhagen based on the geo-location data of the municipality location. Comparison is also carried out between the waste management using conventional method and intelligence method is carried out in city of Copenhagen [42]. Management of the waste efficiently and recycling it effectively will make the nation grow further. In this work various solid wastes like metal, glass, rubber, plastic and paper is separated effectively by the device electro-mechanical system using microcontroller and operational amplifier for sorting the solid wastes in an efficient manner. They work towards a motto to convert the conventional waste management approach to a smart system [38].Parallel mechanism is used to sort out the metals from the waste collected by using the sensors used in the mechanism. There are many mechanisms to sort out the required material from the waste. The efforts have been taken to convert the sort out materials into a useful product from the old recovered material [4]. Used littering quantification for the cleanliness and for the betterment of the city. To obtain this computer automated vision of the different types of wastes in the form of mages is collected in streets, sidewalks and other common places. Google net base vision application is used to classify the different types of urban waste this application accuracy varies from 63-77% in classifying different types of waste [46].Deeper neural networks are used mage classification but it is difficult to train this networks. Developed the learning framework easy for the training for neural network. The most recent development of deep learning lead to the improvement of computer vision. Deep Learning model has its application in picture segmentation, classification and detection. Developed the image framework ranging from 100 to 1000 based for easy classification of different objects [18]. Here the cloud-based waste management were carried out to monitor the waste management ac- tivities. Specific containers are allotted for each type of solid waste like plastic, rubber, metal, cotton etc and each container is connected with sensor. Information is updated to the cloud for effective sorting of the collected waste. This cloud-based waste management is not only effective in sorting and also it gives a desired route for the collection of waste. This method also paves the way for route optimization and to attain the efficiency in fuel and cost spent for the transport [1]. This work presents some demerits of handling waste management techniques in present situation and suggested the system is to be controlled by means of Arduino IDE. The system can read the depth of waste inside the container with the help of sensor and transmits the data to the central system through the wireless medium. Developed vision system for the huge waste collection in an economical manner with the aid of ultrasonic sensors. The role of the ultrasonic sensors is to collect the data from the dustbin and sent to the officials through Wi-Fi medium [43].A review on conventional waste collection technologies and the deficiencies in the current method is carried out. A unified heuristic algorithm is applied for the routing problem optimal and sensitivity analysis were conducted on the collection costs and for the environmental friendly approach. Proposed a smart and green waste collection for sustainable aste management in future [30]. 2.3 Use of optimization techniques and algorithms For the weighted graph shortest path and minimum spanning is computed in one origin. Considered Shortest path and minimum spanning were altered after computation. For the input computation of tree program they provide the number of analytic functions for lower bound. By this it provide solutions for all or for half of worst scenarios attained by other algorithms. This method is used to calculate the minimal distance between the two trash cans to optimize the trash collecting routes from various trash collection cans [47]. The minimum Linear Arrangement Problem and the Traveling Salesman Problem is similar combinatorial problem. In the minimum Linear Arrangement Problem simulated annealing and spectral sequencing are used for the approximations and they are found to be closer in their studies for lower and upper bound. Similarly another method called multi-level network is used when there is various sub-levels and multiple layers involved. This method yield better results only large scale network. But genetic algorithm (GA) is a better one to optimize the clearance paths of trash cans [29, 44, 53].This work uses the modified Backtracking Search Algorithm (BSA) in-built with capacitated vehicle routing problem (CVRP) models. This models are augmented with the smart bin concept to optimize the vehicle routing distance for waste disposal. By this method the huge amount of money spent for the waste management and air pollution is reduced due to the emissions from https://doi.org/10.15837/ijccc.2021.5.4239 6 vehicles [32]. Various decision-making algorithms are used in the solid waste collection these algorithm models are compared with each other. The comparisons are carried out for various performance metrics such as receiving data while the system in motion, multi objective, transmission loss of data, and increased data reception. Address the inefficient waste management challenges in smart cities by decision making model for IoT enabled objects with multiple goals. This method reduces data loss in the IoT data collection [33]. Shortest path model is proposed for solid waste management in Kanpur city. Here the program coding in C program is carried out the shortest path to find out optimal route for waste management. Developed C program is useful in identifying the shortest path between the two different locations for the waste collection. It also calculates the distance of the shortest path between the two different locations[15]. This work proposed is based upon artificial neural network (ANN) prediction algorithm to calculate the waste generation on the household size. Smart waste bin is designed to calculate the emptiness level of and weight of the bin so, it sends the direct information to responsible authorities [51]. Discussed the importance of prediction models in forecasting the rate of waste generation in Tehran city. Compared the various forecasting models such as Mean Absolute Percentage Error (MAPE), Mean Square Error (MSE), and ARIMA for the waste generation rate in Tehran. Final results shows that ARIMA is better prediction model compared to other models [34]. They developed the model with constraints such as bin maximum capacity and poisson ratio for waste arrival rate. When the garbage reaches the maximum value it sends alarm signal to the particular station it communicates the cloud for processing the data also finds the optimal route for waste collection [41]. This work focuses on the IoT elements and their characteristics. Elements comprise identification, sensing, communi- cation, computation, semantics, and services. Characteristics involve communication identification and interaction. The review of smart waste management was conducted and the comparison of each methodologies were conducted[12]. 2.4 Role of Radio Frequency Identification (RFID) in solid waste management Radio Frequency Identification (RFID) is a modern technology which is used in various situa- tions for tracing items and persons for the purpose of dynamic sharing of information like the older technologies like barcode. RFID smart tag is used for monitor and trace the cold storage in food applications[2].Radio Frequency Identification (RFID) and Sensor Network (SN) are used to minimize the impact of uncontrollable disposal of waste disposal. These technologies are used to track waste collection bin information of the concerned user without the support of information sharing system. The smart bin used with RFID tag is also for sorting the waste of different types for further recy- cling operations[14]. These (RFID) are used to measure the weight of the garbage bin in the each and individual household garbage collection. Developed the RFID system with load sensor cell to automate the waste management process to reduce the waste management cost. This design is also useful to streamline the waste such as recyclable and non-recyclable waste[10].VGG-16 pre-trained CNN is trained to identify nearly 1.2 million objects from imagenet data set.so this RFID’s are used to identify 1000 different objects. Both VGG-16 and alexnet are used for photo classification both these forms shows minimum error when trained for million objects. This technologies are used to avoid the segregation confusions in recycling process [48]. Alexnet is a platform among the convolution neural network which has a repeated convolution layers followed by max-pooling with the best results obtained from the dataset used for waste classi- fication with its stored 1.2 million images of multiple layers. They also verified that if any one of the layer is removed it results in the lagging performance by 2% [26].The integrated approach of architec- ture called Convolution network is used for classification and detection. Novel deep learning approach is combined with ConvNet for better classification and detection. Convolution neural network (CNN) is used in analyzing the visual image here it takes things which are going to be investigated as input and classify them into different materials. Large convolution networks is developed for image classifi- cation and it proves to show superior performance in classification with different model layers [54, 59]. It has many hidden dense layers such as polling layers, fully connected layers convolutional layers and normalization layers. RFID in combination with communication technologies were used in solid waste https://doi.org/10.15837/ijccc.2021.5.4239 7 bin and truck monitoring system. Algorithms were developed for the real-time implementation. By this arrangement, information stored is used for waste management processing activities. This method yields better results for solid waste management [17]. Waste tracing is done by RFID in collection services of waste management. Some simulation analysis has been conducted to check the impact of introducing the new technology in the waste management procedures. Finally, the application of RFID in various organization collection methods are compared in terms of economic and technical criteria [35]. Discussed the role of RFID in integrated approach of solid waste management for improving the waste and resource management in Switzerland. Here the waste chain analysis starting from waste production, waste separation and waste treatment were carried out. By the application of RFID the recycling growth rate improved in a consistent manner[7]. RFID’s are used to trace bin distribution in waste management system, before the usage of RFID this tracing work was done by labor force which is higher compared to the usage of RFID[13].Real time monitoring of information regarding the storing and transportation of solid waste have been maintained accurately by the RFID,GPRS and GIS for pollution control and environmental protection. By this well monitoring system the hazardous waste generation were reduced much compared to the traditional approach [31].Some issues in the hazardous waste producers in Brazil in close monitoring of transporting these hazardous waste and disposing it at right destination. Because it poses serious threat and vulnerable situation to the environment. This issue was addressed properly the new system design and prototype of RFID by closely monitoring the transportation of hazardous waste in Brazil and disposing it in the desired location[5]. The issue of improper solid waste management in Kanpur city, India related to improper information regarding transportation and disposal of disposal for the generated waste. Taken into account this problem were solved by the application of communication tools like RFID, GSM uses and other related software packages [55].Metropolis like in Shanghai, China there is a problem in maintaining efficient waste management including collection, transportation and disposal. This issue were solved by 3R’s concept of reducing, reusing and recycling the generated solid wastes have been properly sorted out with help of information technology through RFID.This technology proves to be the cost effective waste management system [58].Huge amount of waste sorting is a difficult task and also doing it in a manual manner is unhygienic especially during the pandemic situation like COVID- 19. Deep learning integrated with convolution neural network (CNN) is trained with large data sets used for testing the accuracy. This is carried out in sorting the different waste like sheet metal, card board, and glass and metal tins[9]. 3 Key findings and suggestions In most of the developing countries they are following only conventional mode of solid waste management. The introduction of the intelligent system as discussed earlier in this work will minimize the cost incurred in the solid waste management. The wireless mode of network by the IoT sensors, RFID tags, Transducers will solve the waste corporation officials by clearing the garbage bins in a timely manner. The intelligent methods discussed in this paper will improve the recycling opportunities in most of the countries. Because these methods are very useful in sorting the recyclable and non-recyclable waste. It is safer to handle the hazardous waste by the modern technologies than the conventional ap- proach. Their accuracy of the well trained convolution neural network by more than a billion of classified mages is very useful in sorting the different types of wastes for efficient recycling operations. Also this mode of smart waste management will reduce the chance of virus infection especially during the pandemic period COVID-19. https://doi.org/10.15837/ijccc.2021.5.4239 8 4 Conclusion The role of artificial intelligence, cloud computing, Internet of things, optimization techniques, algorithms and modern technologies is very essential for the solid waste management (SWM).In the conventional mode of waste management it discusses about the transportation, collection and disposal is of manual method it makes all the developing countries to spend much higher for the waste man- agement. Even the treatment of this solid wastes involving sorting activity to sort out the recyclable and non- recyclable wastes .to carry out this all municipal corporations have set a huge amount for the labors working for the recycling activities.As mentioned earlier it is unhygienic and cause some infectious diseases especially during the pandemic period covid-19 the whole world is facing. Now it’s time for all developing countries to think of all the modern technologies as discussed in this paper to harvest the benefits from it to maintain the efficient SWM. Competing Interest Authors declared that there is no competing interest exists. Acknowledgements We are thankful to RAMCO Institute of Technology provided expertise that greatly assisted the research, although they may not agree with all of the interpretations provided in this paper. References [1] Aazam, M.; St-Hilaire, M.; Lung, C.; Lambadaris, I. (2016). Cloud-based smart waste manage- ment for smart cities, Proc. of the IEEE Workshop on Computer-Aided Modeling and Design of Communication Links (CAMAD 2016), 188–193, 2016. [2] Abad, E.; Palacio, F.; Nuin, M.; Zárate, A.G.D.; Juarros, A.; Gómez, J.M. (2009). RFID smart tag for traceability and cold chain monitoring of foods: demonstration in an intercontinental fresh fish logistic chain, Journal of Food Engineering, 93(4),394-402,2009. [3] Alexey Medvedev,; Petr Fedchen kov -Arkady Zaslavsky,; Theodoros Anagnos-topoulos,; Sergey Khoruzhnikov (2015). Waste Management as an IoT-Enabled Service in Smart Cities, IoT-Enabled Service in Smart Cities. NEW2AN: Internet of Things, Smart Spaces, and Next Generation Networks and Systems, 104-115, 2015. [4] Amrutha Chandramohan,; Joyal Mendonc,; Nikhil Ravi Shankar,; Nikhil U Baheti,; Nitin Kumar Krishnan,; M. S. Suma (2014). Automated Waste Segregator, Texas Instruments India Educators’ Conference (TIIEC), IEEE, 1-6, 2014. [5] Anagnostopoulos, T.; Zaslavsky, A.; Kolomvatsos, K.; Medvedev, A.; Amirian, P.; Morley, J.; Hadjiefthymiades, S. (2017). Challenges and Opportunities of Waste Management in IoT-enabled Smart Cities: A Survey, IEEE Transaction of Sustainability Computation, 275–289, 2017. [6] Anderson Amendoeira Namen,; Felipe da Costa Brasil,; Jorge José Gouveia Abrunhos (2014). RFID technology for hazardous waste management and tracking, Waste management and re- search, Waste Management & Research: The Journal for a Sustainable Circular Economy, 32(9), 59-66, 2014. [7] Binder, C.R.; Quirici, R.; Domnitcheva,; Stäubli, B. (2008). Smart labels for waste and resource management – an integrated assessment, Journal of Industrial Ecology, 12(2), 207-214, 2008. [8] Bharadwaj, B.; Kumudha, M.; Gowri Chandra,; Chaithra Gon, N. (2017). Smart waste manage- ment using IoT to support Swachh Bharat Abhiyan - a practical approach, 2nd International Conference on Computing and Communications Technologies, 1-4, 2017. https://doi.org/10.15837/ijccc.2021.5.4239 9 [9] Chandaluru Priyanka, P.; Sriramya (2020). Image Based Classification of Waste Material Us- ing Convolution Neural Network, International Journal of Advanced Science and Technology, 29(5),2967-2975, 2020. [10] Chowdhury, B.; Chowdhury, M.U. (2007). RFID based real-time smart waste management system, Telecommunication Networks and Applications Conference, IEEE, 175–180, 2007. [11] Eunice Likotiko,; Dmitry Petrov,; Joseph Mwangoka,; Ulrich Hilleringmann (2018). Real Time Solid Waste Monitoring Using Cloud and Sensors Technologies, The Online Journal of Science and Technology, 8(1), 106-116, 2018. [12] Fallavi, K.N.; Kumar, V.R.; Chaithra, B.M. (2017). Smart waste management using Internet of Things: A survey, International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), 60–64, 2017. [13] Friedlos, D. (2008). Australian waste-collection businesses tag trash bins, RFID Journal, 1, 1-3, 2008. [14] Glouche, Y.; Couderc, P. (2013). A smart waste management with self-describing objects, The Second International Conference on Smart Systems, Devices and Technologies, 1-15, 2013. [15] Gulab Singh,; Brajesh Singh,; Shubham Rathi,; Saurabh Haris (2014). Solid Waste Management using Shortest Path Algorithm, International Journal of Engineering Science Invention Research & Development, 1(2), 60-64, 2014. [16] Gutierrez, J.M.; Jensen, M.; Henius, M.;, Riaz, T. (2015). Smart waste collection system based on location intelligence, Procedia Computer Science, 61, 120-127, 2015. [17] Hannana Maher Arebey, M.A.; Begum,; HassanBasri, R.A. (2011). Radio Frequency Identification (RFID) and communication technologies for solid waste bin and truck monitoring system, Waste Management, 31(12), 2406-2413, 2011. [18] He, K.; Zhang, X.; Ren, S.; Sun, J. (2016). Deep residual learning for image recognition, Confer- ence on Computer Vision and Pattern Recognition, 770-778, 2016. [19] Himanshi Ramani,; Lekhraj Mehra (2017). Technologies and Their Usage in Solid Waste Monitor- ing and Management Systems, National Conference on Road Map for Smart Cities of Rajasthan, 350-353, 2017. [20] Hoornweg, D.; Bhada-Tata, P. (2012). What a Waste: A Global Review of Solid Waste Manage- ment World Bank, Urban development series, World Bank, Washington, 1-116, 2012. [21] Insung Hong,; Sunghoi Park,; Beomseok Lee,; Jaekeun Lee (2014). IoT-Based Smart Garbage System for Efficient Food Waste Management, Scientific world journal, 13,1-10, 2014. [22] Jaipuria, S.; Mahapatra S. (2014). An improved demand forecasting method to reduce bullwhip effect in supply chains, Expert Systems with Applications, 41(5), 2395-2408, 2014. [23] Jouhara, H.; Czajczyńskaa, D.; Ghazal, H.; Krzyżyńska, R.; Anguilanod, L.; Reynolds, A.J.; Spencer,N. (2017). Municipal waste management systems for domestic use, Energy, 139, 485-506, 2017. [24] Jenilasree, G.; Shenbagavadivu, N.; Bhuvaneswari, M. (2018). A Study on Automatic Solid Waste Management System for Smart City, International Journal of Creative Research Thoughts, 5(4), 1682-1689, 2018. [25] Kannangara, M.; Dua, R.; Ahmadi, L.; Bensebaa, F. (2018). Modeling and prediction of regional municipal solid waste generation and diversion in Canada using machine learning approaches, Waste Management, 74, 2018. https://doi.org/10.15837/ijccc.2021.5.4239 10 [26] Krizhevsky, A.; Sutskever, I.; Hinton, G.E. (2012). ImageNet classification with deep convolu- tional neural networks, Neural Information Processing System Conference, 1097–1105, 2012. [27] Kumar, N.S.; Vuayalakshmi, B.; Prarthana, R.J.; Shankar, A. (2017). IOT based smart garbage alert system using Arduino UNO, Neural Information Processing System Conference, IEEE, 1-8, 2017. [28] Kusum Lata,; Singh, S.K. (2016). IOT based smart waste management system using wireless sen- sor network and embedded linux board, International Journal of Current Trends in Engineering & Research, 2(7), 210-214, 2016. [29] López, J.G.; Imine, M.; Rumín, R.C.; .Pedersen, J.M.; Madsen, O.B. (2008). Multilevel network characterization using regular topologies, Computational Network, 173-187, 2008. [30] Lu, J.W.; Chang, N.B.; Liao, L.; Liao, M.Y. (2017). Smart and Green Urban Solid Waste Collec- tion Systems: Advances, Challenges, and Perspectives, Technical journal of the IEEE Systems, 11, 2804–2817, 2017. [31] LuHuida,; FanBingchen,; YuanLiheng,; LiYanan (2012). RFID-Based Hazardous Waste Manage- ment Platform Establishment, Technical journal of the IEEE Systems, 11, 2804–2817, 2017. [32] Mahmuda Akhtara,; Hannan, M.A; Begum Hassan Basri, R.A. (2017). Backtracking search al- gorithm in CVRP models for efficient solid waste collection and route optimization, Procedia Engineering, 29, 4-8, 2012. [33] Manqele, L.; Adeogun, R.; Dlodlo, M.; Coetzee, L. (2017). Multi-objective decision- making framework for effective waste collection in smart cities, Global Wireless Summit (GWS), 155–159, 2017. [34] Marandi, F.; Ghomi, S. (2016). Time series forecasting and analysis of municipal solid waste generation in Tehran city, 12th International Conference on Industrial Engineering (ICIE), 14- 18, 2016. [35] Maria Grazia Gnoni,; Gianni Lettera,; Alessandra Rollo (2013). A feasibility study of a RFID traceability system in municipal solid waste management, International Journal of Information Technology and Management, 12, 27-38, 2013. [36] Maurizio Giacobbe,; Carlo Puliafito,; Marco Scarpa (2016). The Big Bucket: An IoT Cloud Solution for Smart Waste Management in Smart Cities, European Conference on Service-Oriented and Cloud Computing, ESOCC Advances in Service-Oriented and Cloud Computing, 43- 58, 2016. [37] Maryam Abbasi,; Ali El Hanandeh (2016). Forecasting municipal solid waste generation using artificial intelligence modelling approaches, Waste Management, 56, 13-22, 2016. [38] Mahmudul Hasan Russel,; Mehdi Hasan Chowdhury,; Md. Shekh Naim Uddin,; Ashif Newaz (2013). Development of Automatic Smart Waste Sorter Machine, International Conference on Mechanical, Industrial and Materials Engineering, 1-7, 2013. [39] Mitton, N.; Papavassiliou, S.; Puliafito, A.; Trivedi, K.S. (2012). Combining Cloud and sensors in a smart city environment, Journal on Wireless Communications and Networking, 2012(247), 1-10, 2012. [40] Mohammad Ali Abdoli,; Maliheh Falah Nezhad,; Reza Salehi Sede,; Sadegh Behboudian. (2011). Long term forecasting of solid waste generation by the artificial neural networks, Environmental Progress & Sustainable Energy, 31(4), 628-636, 2011. [41] Omara, A.; Gulen, D.; Kantarci, B.; Oktug,S. (2018). Trajectory Assisted Municipal Agent Mo- bility A Sensor-Driven Smart Waste Management System, Journal of Sensors and Actuator Net- works, 7, 29-37, 2018. https://doi.org/10.15837/ijccc.2021.5.4239 11 [42] [Online]. Available: http://data.kk.dk, Open Data Copenhagen. [43] Parkash, P.V. (2016). IoT Based Waste Management for Smart City, International Journal of Innovation Research, Computational Communication Engineering, 7, 29-37, 2016. [44] Petit, J. (2001). Experiments on the minimum linear arrangement problem, Journal of Experi- mental Algorithmics, 1-33, 2001. [45] Praveen Kumar Gupta,; Vidhya Shree,; Lingayya Hiremath,; Sindhu Rajendran (2019). The Use of Modern Technology in Smart Waste Management and Recycling: Artificial Intelligence and Machine Learning, Studies in Computational Intelligence, 1, 173-188, 2019. [46] Rad, M.S.L Kaenel, A.V.; Droux, A. (2017). A computer vision system to localize and classify wastes on the streets, International Conference in Computer Vision System, Springer, 195-204, 2017. [47] Ramarao, K.V.S.; Venkatesan, S. (1992). On finding and updating spanning trees and shortest paths, Journal of Algorithms, 13(2), 235- 257, 1992. [48] Russakovsky, O.; Deng, J.; Su,H.; Krause, J.; Satheesh, S.; Ma, S.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M. (2015). Imagenet large scale visual recognition challenge, International Journal of Computer Vision, 115(3), 211–252, 2015. [49] L.P.Singh, L.P.; Challa, R.T. (2016). Integrated Forecasting Using the Discrete Wavelet Theory and Artificial Intelligence Techniques to Reduce the Bullwhip Effect in a Supply Chain, Global Journal of Flexible System Management, 17(2), 157-169, 2016. [50] Sinha, T.; Kumar, K.M.; Saisharan, P. (2018). Smart dustbin, International journal of Indian Electronics and Electrical Engineering, 3(5), 101-104, 2018. [51] Siti Hajar Yusoff,; Ummi Nur Kamilah Abdullah Din,; Hasmah Mansor. (2018). Design of Smart Waste Bin and Prediction Algorithm for Waste Management in Household Area, Indonesian Journal of Electrical Engineering and Computer Science, 12(2), 748-758, 2018. [52] Sodanil, M.; Chatthong, P. (2014). Artificial neural network-based time series analysis forecasting for the amount of solid waste in Bangkok, Ninth international conference on digital information management, 16-20, 2014. [53] The traveling-salesman problem (1997). Mathematics in Science and Engineering, Mathematics in Science and Engineering, 1977. [54] Sermanet, P.; Eigen, D.; Zhang, X.; Mathieu, M.; Fergus, R.; Lecun,Y. (2014). OverFeat: inte- grated recognition, localization and detection using convolutional networks, International Con- ference on Learning Representations, 1-16 , 2014. [55] Suyog Gupta,; Pradeep Kumar. (2015). Real time solid waste monitoring and management sys- tem: a case study of Kanpur city, International Journal of Science, Environment and Technology, 4(2), 514 -517, 2015. [56] Theodoros Anagnostopoulos,; Arkady Zaslavsky,; Inna Sosunova (2018). A stochastic multi-agent system for Internet of Things-enabled waste management in smart cities, Waste management and research, 36(11), 1113- 1121, 2018. [57] Thürer,M; Pan,Y.H; Qu,T.; Luo,H.; Li , C.D.; Huang,G.Q, (2016). Internet of Things (IoT) driven kanban system for reverse logistics: solid waste collection, Journal of Intelligent Manufacturing, 30, 2621–2630, 2016. [58] Ying An,; Guang Ming Li,; Wen Qing Wu,; Wen Zhi He,; Xiang Shi (2014). Information Technol- ogy Based Municipal Solid Waste Management in Shanghai, China, Advanced Materials Research, 1073-1076, 911-914,2014. https://doi.org/10.15837/ijccc.2021.5.4239 12 [59] Zeiler D. M.; Fergus, R. (2014). Visualizing and understanding convolutional neural networks, 13th European Conference on Computer Vision (ECCV), 818-833, 2014. [60] Zongguo Wen,; ShuhanHu,; Djavan De Clercq; Bruce Beck, M. (2017). Design implementation, and evaluation of an Internet of Things (IoT) network system for restaurant food waste manage- ment, Waste Management, 73, 26-38, 2017. Copyright ©2021 by the authors. Licensee Agora University, Oradea, Romania. This is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial 4.0 International License. Journal’s webpage: http://univagora.ro/jour/index.php/ijccc/ This journal is a member of, and subscribes to the principles of, the Committee on Publication Ethics (COPE). https://publicationethics.org/members/international-journal-computers-communications-and-control Cite this paper as: Godwin Barnabas, S.; Arun vasantha Geethan, K.; Valai Ganesh, S.; Rajakarunakaran, S.; Sabar- ish Kumar, P. (2021). Role of Modern Technologies and Internet of Things in the Field of Solid Waste Management, International Journal of Computers Communications & Control, 16(5), 4239, 2021. https://doi.org/10.15837/ijccc.2021.5.4239 Introduction Role of IoT,Modern technologies, optimization techniques, and of Radio Frequency Identification (RFID) in solid waste management Part of IoT in in solid waste management Role of modern technologies Use of optimization techniques and algorithms Role of Radio Frequency Identification (RFID) in solid waste management Key findings and suggestions Conclusion