International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | AI-Powered Smart Waste Segregation System for Sustainable Smart Cities Using Machine Learning |
|---|---|
| ABSTRACT | Rapid urbanization and population growth have intensified waste management challenges across modern cities. Traditional manual waste segregation is inefficient, inconsistent, and poses health risks to workers. This paper proposes an AI-Powered Smart Waste Segregation System (AISWSS) that leverages machine learning algorithms — specifically Convolutional Neural Networks (CNN), Support Vector Machines (SVM), and Random Forest classifiers — to automate real-time classification of municipal solid waste into six categories: organic, plastic, metal, glass, paper, and e-waste. The system integrates a compact embedded camera module, a Raspberry Pi 4 processing unit, and a servo-driven mechanical segregation actuator. Trained on a dataset of 28,000 labeled waste images across diverse lighting and orientation conditions, the proposed CNN model achieves a classification accuracy of 97.4%, outperforming conventional ML baselines. The system reduces manual sorting labor by an estimated 85% and increases material recovery rates by 40%. Experimental results demonstrate robust real-time performance at 12 frames per second. This research contributes a scalable, cost-effective, and energy- efficient solution aligned with UN Sustainable Development Goal 11 (Sustainable Cities and Communities). |
| AUTHOR | MANJULA P, SHIVASHANKAR S J, SANDEEP R, SAMMED SHITAL HUDDAR, SUHAS M, VISHAL V P, AMEED M A Assistant Professor, Department of Computer Science and Engineering, Jain Institute of Technology, Davangere, Karnataka, India Department of Computer Science and Engineering Jain Institute of Technology, Davangere, Karnataka, India |
| VOLUME | 184 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1405082 |
| pdf/82_AI-Powered Smart Waste Segregation System for Sustainable Smart Cities Using Machine Learning.pdf | |
| KEYWORDS | |
| References | [1] World Bank, "What a Waste 2.0: A Global Snapshot of Solid Waste Management to 2050," Washington DC: The World Bank, 2018. [2] O. Awe, R. Mendon, and A. Sharma, "Smart waste categorization and recycling using machine learning," Int. J. Adv. Comput. Sci. Appl., vol. 9, no. 4, pp. 145- 152, 2018. [3] M. Yang and G. Thung, "Classification of trash for recyclability status," CS229 Project Report, Stanford University, 2016. [4] A. H. Vo, N. T. Son, T. P. Nguyen, and T. T. Vo, "A waste classification system using transfer learning with MobileNet," Procedia Comput. Sci., vol. 141, pp. 410- 417, 2018. [5] T. Mittal, U. Bhatt, and R. Chandra, "SpotGarbage: GitHub commits for waste detection," in Proc. ACM Multimedia, Mountain View, CA, 2016, pp. 987-989. [6] Y. Chu, C. Bai, W. Zhang, and H. Li, "Garbage classification based on HOG feature and SVM," in Proc. IEEE Int. Conf. Electr. Eng. Autom. (ICEEA), 2018, pp. 1-4. [7] S. Waheed, M. Khan, and B. Ahmad, "Hyperspectral waste material classification using random forest," Waste Manag., vol. 112, pp. 87-95, 2020. [8] K. Pardini, J. A. Rodrigues, S. A. P. Kumar, M. V. O. de Paula, and V. H. C. de Albuquerque, "IoT-based solid waste management solutions: a survey," J. Sens. Actuator Netw., vol. 8, no. 1, p. 5, 2019. [9] D. Misra, G. Das, T. Chakrabortty, and D. Das, "An IoT- based waste management system monitored by cloud," J. Mater. Cycles Waste Manag., vol. 20, pp. 1574-1582, 2018. [10] O. Adedeji and Z. Wang, "Intelligent waste classification system using deep learning convolutional neural network," Procedia Manuf., vol. 35, pp. 607-612, 2019. |
