Edge-AI Powered Intelligent Waste Bins for Autonomous Urban ‎Waste Segregation and Recycling

  • Authors

    • Sonali Mondal Assistant Professor, Department of CS & IT, Kalinga University, Raipur, India
    • Moti Ranjan Tandi Assistant Professor, Department of CS & IT, Kalinga University, Raipur, India
    • Nikhil Singh Assistant Professor, New Delhi Institute of Management, New Delhi, India
    https://doi.org/10.14419/crxt0n36

    Received date: May 2, 2025

    Accepted date: May 29, 2025

    Published date: October 31, 2025

  • Edge AI Waste Management; Real-Time Waste Classification; Reinforcement Learning Sorting; IoT-Based Monitoring; Piezoelectric ‎Energy Harvesting.

  • Abstract

    Innovative solutions to sorting, recycling, and environmentally friendly handling of urban waste, because we don’t know how to solve ‎urban waste management. An intelligent waste bin system with edge AI is being described to sense, classify, and manage the waste on its ‎own, as per this research. The above systems effectively combine a lightweight Edge-AI model based on CNNs and Vision Transformers ‎‎(ViTs) to detect waste in real time. The system identifies the materials using the appearance, the thermal appearance, and the strengths of the ‎density scan of the material using the RGB cameras, the LiDAR sensors, and the infrared scanners. Reinforcement Learning (RL) is used to ‎create such a robotic sorting mechanism that would allow sorting of the waste intelligently to improve classification precision ‎with time. With the system, the piezoelectric energy harvesting unit is used, and the system runs as long as the battery lasts. It also ‎permits municipal Authorities to leverage within an IoT-enabled monitoring framework that indicates if the bin is present, the fill level, and ‎alerts for odor. Furthermore, the platform provides an incentive to the public to participate in the system through a reward system using a ‎QR code, where people earn points when they dispose of waste responsibly. The finding is evaluated, and it is found that the accuracy of ‎the waste classification, the less power dependency, and waste collection scheduling are improved. It is a smart bin; the edge processing is using ‎it in real time, applying adaptive learning and energy integration for it to be energy sustainable for supporting the eco-friendly urban waste ‎management‎.

  • References

    1. Kumar, G., Vyas, S., Sharma, S. N., &Dehalwar, K. (2024). Challenges of Environmental Health in Waste Management for Peri-urban Areas. In Solid Waste Management: Advances and Trends to Tackle the SDGs (pp. 149-168). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-60684-7_9.
    2. tülay Çağatay, I., Özbaş, M., Yılmaz, H. E., & Ali, N. (2021). Determination of antibacterial effect of Nannochloropsisoculata against some rainbow trout pathogens. Natural and Engineering Sciences, 6(2), 87-95. https://doi.org/10.28978/nesciences.970543.
    3. Rekha, S. S., Kavitha, P., & Kamalakkannan, S. (2024, May). Towards Sustainable Waste Management: Exploring Machine Learning and Deep Learning Solutions for Biodegradable and Non-Biodegradable Waste Identification. In 2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN) (pp. 585-591). IEEE. https://doi.org/10.1109/ICPCSN62568.2024.00098.
    4. Surendar, A. (2024). Survey and future directions on fault tolerance mechanisms in reconfigurable computing. SCCTS Transactions on Reconfigura-ble Computing, 1(1), 26-30.
    5. Hao, D., Qi, L., Tairab, A. M., Ahmed, A., Azam, A., Luo, D., ... & Yan, J. (2022). Solar energy harvesting technologies for PV self-powered applica-tions: A comprehensive review. Renewable energy, 188, 678-697. https://doi.org/10.1016/j.renene.2022.02.066.
    6. Chow, Y.W., Susilo, W., Baek, J., Kim, J., & Zong, W. (2021). Exploiting QR Code Error Correction for Digital Image Watermarking. Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications, 12(2), 114-140.
    7. Hua, H., Li, Y., Wang, T., Dong, N., Li, W., & Cao, J. (2023). Edge computing with artificial intelligence: A machine learning perspective. ACM Computing Surveys, 55(9), 1-35. https://doi.org/10.1145/3555802.
    8. Đurić, D. (2021). Thermal Comfort Defined by UTCI for the Month August of 2017 in the City of Bijeljina. Archives for Technical Sciences, 2(25), 65–70. https://doi.org/10.7251/afts.2021.1325.065D.
    9. Ding, X., Shi, Y., Sun, H., & Ding, X. (2023). An ultra-low-power-consumption urban sewer methane concentration monitoring system based on ul-trasound. Applied Sciences, 13(10), 6295. https://doi.org/10.3390/app13106295.
    10. Bhowmik, S., Majumder, T., & Bhattacharjee, A. (2024). A Low Power Adiabatic Approach for Scaled VLSI Circuits. Journal of VLSI Circuits and Systems, 6(1), 1–6. https://doi.org/10.31838/jvcs/06.01.01.
    11. Azhar, N. Z. B., Teo, N. H. I., binti Hamzah, R., binti Roslan, R., &Maskat, R. (2024, September). A Hybrid ResNet—MobileNet Deep Learning Model for Smart Bin Waste Classification. In 2024 5th International Conference on Artificial Intelligence and Data Sciences (AiDAS) (pp. 356-362). IEEE. https://doi.org/10.1109/AiDAS63860.2024.10730599.
    12. Pal, F., & Hatua, S. R. (2019). Proficiency Building of Non-Academic Libraries in the Context of Present LIS Education in India: A Study. Indian Journal of Information Sources and Services, 9(1), 128–131. https://doi.org/10.51983/ijiss.2019.9.1.580.
    13. Oladigbolu, J. O., Ramli, M. A., & Al-Turki, Y. A. (2020). Feasibility study and comparative analysis of a hybrid renewable power system for off-grid rural electrification in a typical remote village located in Nigeria. IEEE Access, 8, 171643-171663. https://doi.org/10.1109/ACCESS.2020.3024676.
    14. Charvillat, V., &Grigoraş, R. (2007). Reinforcement learning for dynamic multimedia adaptation. Journal of Network and Computer Applica-tions, 30(3), 1034-1058. https://doi.org/10.1016/j.jnca.2005.12.010.
    15. Bányai, T., Tamás, P., Illés, B., Stankevičiūtė, Ž., & Bányai, Á. (2019). Optimization of municipal waste collection routing: Impact of industry 4.0 technologies on environmental awareness and sustainability. International journal of environmental research and public health, 16(4), 634. https://doi.org/10.3390/ijerph16040634.
    16. Kombo, O. H., Kumaran, S., &Bovim, A. (2021). Design and application of a low-cost, low-power, LoRa-GSM, IoT-enabled system for monitoring of groundwater resources with energy harvesting integration. IEEE Access, 9, 128417-128433. https://doi.org/10.1109/ACCESS.2021.3112519.
    17. Sana, L., Nazir, M. M., Yang, J., Hussain, L., Chen, Y. L., Ku, C. S., ... & Por, L. Y. (2024). Securing the IoT cyber environment: Enhancing intrusion anomaly detection with vision transformers. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3404778.
    18. Addas, A., Khan, M. N., & Naseer, F. (2024). Waste management 2.0 leveraging the internet of things for an efficient and eco-friendly smart city solu-tion. Plos one, 19(7), e0307608. https://doi.org/10.1371/journal.pone.0307608.
    19. Kavitha, M. (2025). Breaking the silicon ceiling: A comparative analysis of women’s leadership and participation in AI startups across global innova-tion hubs. Journal of Women, Innovation, and Technological Empowerment, 1(1), 1–6.
    20. Reginald, P. J. (2025). Thermoelastic behavior of gradient porous materials fabricated via additive manufacturing: A multi-scale simulation approach. Advances in Mechanical Engineering and Applications, 1(1), 1–10.
    21. Arvinth, N. (2025). Effect of Pranayama on respiratory efficiency and stress levels in adolescent athletes. Journal of Yoga, Sports, and Health Scienc-es, 1(1), 1–8.
    22. Kavitha, M. (2024). Carbon-neutral pavement materials using recycled industrial waste and nanotechnology enhancements. Journal of Smart Infra-structure and Environmental Sustainability, 1(1), 1–13.
    23. Usikalua, M. R., & Unciano, N. (2025). Memory reconsolidation and trauma therapy: A new frontier in PTSD treatment. Advances in Cognitive and Neural Studies, 1(1), 1–10.
    24. Patel, P., & Dusi, P. (2025). Optimization models for sustainable energy management: A multidisciplinary approach. Bridge: Journal of Multidiscipli-nary Explorations, 1(1), 1–10.
    25. Kavitha, M., & Muralidharan, J. (2025). Ammonia as an alternative fuel: Potential and challenges in renewable energy transition. National Journal of Renewable Energy Systems and Innovation, 1(2), 31–38.
    26. Shimada, T., & Kingdon, C. C. (2025). Next-generation intelligent power systems: Machine learning-driven optimization and blockchain-enabled cy-bersecurity for secure energy infrastructures. National Journal of Intelligent Power Systems and Technology, 1(2), 52–57.
    27. Gichoya, D., & Beken, K. (2025). PWM strategies for reducing harmonics in power electronics for motor drives. National Journal of Electric Drives and Control Systems, 1(2), 24–32.
    28. Chandrakumar, R., & Nestaris, P. K. (2025). Energy storage and battery management in renewable energy systems: Advances in power conversion architectures and optimization strategies. Transactions on Power Electronics and Renewable Energy Systems, 1(3), 8–14.
    29. Maidanov, K., & Frire, G. F. (2025). Multimodal fusion techniques for emotion recognition using audio, visual, and physiological signals. National Journal of Signal and Image Processing, 1(3), 23–30.

  • Downloads

  • How to Cite

    Mondal, S. ., Tandi , M. R. ., & Singh , N. . (2025). Edge-AI Powered Intelligent Waste Bins for Autonomous Urban ‎Waste Segregation and Recycling. International Journal of Basic and Applied Sciences, 14(SI-1), 359-365. https://doi.org/10.14419/crxt0n36