Authors:
Jayasri Jonnalagadda, R. Vinoth, K. Riya, V. Monisha, M. Gandhi, Fatima Hamouche

Addresses:
Department of Artificial Intelligence and Machine Learning, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Electronics and Communication Engineering, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India. Department of Chemistry, Ibn Tofail University, Kenitra, Rabat-Salé-Kénitra, Morocco.

Abstract:

The tremendous growth in trash output that has occurred because of urbanisation and industrialisation has resulted in serious problems for the environment and poses a threat to the health of the general population. To achieve sustainable waste management, waste segregation is essential; however, manual segregation is not only slow but also unsafe and impractical. The purpose of this research is to develop an artificial intelligence-based framework for intelligent waste segregation that leverages deep learning and computer vision to automate classification and sorting. Garbage classification, including plastics, paper, metals, organic materials, and hazardous chemicals, is achieved using convolutional neural networks (CNNs) and pre-trained models such as ResNet and MobileNet. Increased system performance can be achieved by applying a range of image pre-processing techniques, including scaling, normalisation, and augmentation. On the other hand, the system's hardware consists of cameras, microcontrollers, and actuators for real-time waste separation. The framework was subjected to a series of experiments, which revealed an accuracy of around 95%. Additionally, the system performs well in real-time garbage categorisation and sorting, achieving high precision and recall. This is a significant accomplishment. 

Keywords: Artificial Intelligence; Waste Segregation; Deep Learning; Computer Vision; Convolutional Neural Networks; Transfer Learning; IoT Monitoring; Image Classification; Automation Systems.

Received on: 27/04/2025, Revised on: 02/07/2025, Accepted on: 13/09/2025, Published on: 05/06/2026

DOI: 10.69888/FTSESS.2026.000717

FMDB Transactions on Sustainable Environmental Sciences, 2026 Vol. 3 No. 2, Pages: 92-102

• Views : 57
• Downloads : 10

Download PDF