AI-Driven Waste Segregation Using Convolutional and Deep Neural Networks

View at publisher Summarise with VIRAT
Authors: C. Jeevanantham S, Dharanidharan S, Koteeswarar MM, Shahanas M, Ajay Christo P
Cited by: 0
References: 34

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Managing waste efficiently has become a serious challenge due to the growing amount and variety of garbage produced every day. Manual waste segregation is slow, costly, and often inaccurate. To address this problem, this work explores an AI-based approach for automatic waste segregation using Convolutional Neural Networks (CNN) and Deep Neural Networks (DNN). Waste images are classified into multiple categories such as glass, plastic, metal, organic, and hazardous using popular benchmark datasets like TrashNet, TrashBox, and a Kaggle waste dataset. The system applies image preprocessing techniques (resizing, normalization, and augmentation) and uses transfer learning with advanced architectures including ResNet, DenseNet, and ResNeXt, implemented in TensorFlow and PyTorch on GPU platforms. Our experiments show that CNN models deliver high classification accuracy. For example, a fine-tuned ResNet50 achieved 87% accuracy on TrashNet, DenseNet121 reached 95%, and ResNeXt-101 obtained 89.6% on TrashBox. A hybrid CNN model used in a smart-bin prototype achieved up to 98.9 % accuracy. These results highlight strong performance not only in accuracy but also in precision, recall, and F1-score. The proposed AI system can be applied in real-world environments such as smart waste bins, automated sorting conveyors in recycling plants, and IoT-enabled municipal systems. This demonstrates that CNN/DNN-based waste segregation can significantly improve waste handling, making recycling faster, more reliable, and environmentally sustainable.

Fields of Study & Subjects

Advanced Neural Network Applications Municipal Solid Waste Management Waste Management and Recycling

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
1497–1503
Publication date
21 January 2026
Language
EN