Intelligent waste sorting for urban sustainability using deep learning

Abstract Smart cities’ have experienced an increasingly higher rate of urbanization and increase of the population leading to strengthening the pressing needs in waste management. In this paper, we present an intelligent waste classification system that utilises Convolutional Neural Networks (CNNs) for automatic segregation into twelve categories of waste, employing image data. The model is trained on 15,535 images from a publicly available dataset using preprocessing and data augmentation to increase generalisation and mitigate class imbalance. A performance comparison in terms of precision, recall, F1 score, and accuracy shows that the proposed ResNet-based model yields a classification accuracy of 98.16%, outperforming previous work on conventional deep learning architectures. Experimental results demonstrate that the model is a robust framework for handling various types of waste (organic, recyclable, and hazardous) and is a very general model, as confirmed by cross-validation and real-world tests. The proposed system demonstrates great promise for upscaling in automatic waste management towards long-term urban sustainability, improved recycling, and reduced environmental threats.

Abstract licence: CC BY-NC-ND

35 more references, whose wording the paper’s licence keeps private.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.