Smart City Gnosys
Smart city article details
| Title | Smart Self-Power Generating Garbage Management System Using Deep Learning For Smart Cities |
|---|---|
| ID_Doc | 51394 |
| Authors | Thamarai M.; Naresh V.S. |
| Year | 2023 |
| Published | Microprocessors and Microsystems, 98 |
| DOI | http://dx.doi.org/10.1016/j.micpro.2023.104816 |
| Abstract | Population growth and industrialization lead to a proportionate increase in cities' daily waste generation rates. Communities in developing cities often turn to waste disposal methods that have proven destructive to human health and the environment. Further, the disposal of waste is not treated and utilized for waste-to-energy (WtE)-based energy generation. To overcome this situation, many researchers proposed various solutions. However, the optimal utilization of this waste for power generation still needs to be solved. The proposed work discusses a self-powered garbage management system using a Convolution Neural Network and IOT for households in smart cities. The proposed system collects household wastes and segregates them into organic and inorganic wastes using a Convolutional Neural Network (CNN). The inorganic waste is sent to the recycling bin, and the organic waste is used for power generation. The residue of the organic waste after power generation is utilized as fertilizer for plants. The proposed system comprises five modules: a garbage collector, a segregation unit, a power generator unit, an inorganic waste collection bin with IoT-enabled sensors, and an electronic control unit. The garbage collector unit collects household waste. The CNN-based waste classifier in the segregator unit separates the waste into organic and inorganic, and the organic waste is sent to the power generation unit. The waste is grinded using a combustion unit in the power generator, producing biogas for electric power generation. The system is fully automatic, and a Raspberry Pi controller controls the complete process with the help of sensors and various motors. The system monitors the inorganic waste collection bin level using sensors. It sends a notification to the municipality's Garbage Collection Van operator using the IoT module once the bin is full and can be sent for recycling. The accuracy of the proposed CNN for waste segregation is 98%. While comparing with other pre-trained CNN models, such as InceptionV3 and Inception ResNet, the proposed method produces satisfactory results with 14% and 12% accuracy gains, respectively. The segregated and decomposed 50 kg of organic waste can produce 6 m3 of biogas which in turn can produce 114 MJ of electric energy, which can be utilized for street lights and also for the proposed smart self-power generating garbage management system to function. The proposed system is highly adaptable in smart cities for household municipal waste management with minimum routine monitoring and operational time requirements. Further, the system generates only a fraction of the required energy. © 2023 Elsevier B.V. |
| Author Keywords | CNN; Electronic controller unit; Garbage collector; Internet of things; Power generator; Waste management |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
49192  | 0.927 | Mohammed Aarif K.O.; Mohamed Yousuff C.; Mohammed Hashim B.A.; Mohamed Hashim C.; Sivakumar P. | Smart Bin: Waste Segregation System Using Deep Learning-Internet Of Things For Sustainable Smart Cities | Concurrency and Computation: Practice and Experience, 34, 28 (2022) |
| 8552 | 0.918 | Selvi S.; Elamathy G.O.; Kirana B.; Swetha S. | An Intelligent Solid Waste Classification And Monitoring Alert System Using Deep Learning | 2024 International Conference on Integration of Emerging Technologies for the Digital World, ICIETDW 2024 (2024) |
| 7826 | 0.918 | Saghana K.; Saranya P.; Mahesh Reddy A.; Keerthy Rai V.; Ramasubramanian B.; Sudhakaran P. | An Efficient Deep Learning Based Waste Management System For Sustainable Environment | 3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025 (2025) |
| 22313 | 0.915 | Chauhan R.; Shighra S.; Madkhali H.; Nguyen L.; Prasad M. | Efficient Future Waste Management: A Learning-Based Approach With Deep Neural Networks For Smart System (Lads) | Applied Sciences (Switzerland), 13, 7 (2023) |
| 8881 | 0.915 | William P.; Patil J.M.; Panda S.; Venugopal A.; Vidyullatha P.; Kumar N.M.; Jandwani A. | An Optimized Framework For Implementation Of Smart Waste Collection And Management System In Smart Cities Using Iot Based Deep Learning Approach | International Journal of Information Technology (Singapore), 16, 8 (2024) |
| 32689 | 0.909 | Shirwaikar R.; Lamgaonkar Y.; D’souza L.; Khorjuvenkar D.P. | Intelligent Waste Bot Using Internet Of Things And Deep Learning For A Smart City | Lecture Notes in Electrical Engineering, 1080 LNEE (2023) |
| 51721 | 0.908 | Hasan M.K.; Khan M.A.; Issa G.F.; Atta A.; Akram A.S.; Hassan M. | Smart Waste Management And Classification System For Smart Cities Using Deep Learning | 2022 International Conference on Business Analytics for Technology and Security, ICBATS 2022 (2022) |
| 14286 | 0.907 | Thangarasu G.; Alla K.R. | Classification Of Garbage Waste In Smart Cities Using Convolutional Neural Network | 13th IEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2023 (2023) |
| 52263 | 0.904 | Ramya R.; Vinitha Shree S.; Yogeshwari S.; Venkatesan S. | Solid Waste Identification And Classification Method Based On Feature Selection And Hybrid Resnet Cnn Models In Smart Environment | Lecture Notes in Networks and Systems, 730 LNNS (2023) |
| 22318 | 0.904 | Bonala K.; Saggurthi P.; Kambala P.K.; Voruganti S.; Utukuru S.; Sugamya K. | Efficient Handling Of Waste Using Deep Learning And Iot | 2nd International Conference on Sustainable Computing and Smart Systems, ICSCSS 2024 - Proceedings (2024) |