Title: Deep learning models-based classification of solid waste

Authors: Anuradham M. Muthukrishnan; B.V. Santhosh Krishna; Murali Krishna Atmakuri; D. Usha

Addresses: Department of Computer Science and Engineering, S.A. Engineering College, Chennai, Tamil Nadu, India ' Department of Computer Science and Engineering, New Horizon College of Engineering, Bengaluru, Karnataka, India ' Department of Computer Science and Engineering, RVR&JC College of Engineering, Guntur, Andhra Pradesh, India ' Department of Computer Science and Engineering, Mother Teresa Women's University, Kodaikanal, Tamil Nadu, India

Abstract: In order to give the best socio-economic qualities - such as environmental preservation, economic sustainability and a decrease in health-related issues - Municipal Solid Waste (MSW) management currently needs to be carefully studied. Wastes might be identified by computer algorithms, which would also facilitate their conversion into useful energy. Owing to their high error rate and low accuracy, the present methods of trash classification in municipal solid waste continue to have issues. Convolutional Neural Networks (CNNs) and CNNs built from the ground up using ResNet V2 models trained by transfer learning are intended for the purpose of picture classification. The percentage of occurrences in the validation data set that were correctly classified is known as the validation accuracy, and it stands at 0.938. The model effectively adapts what it learnt from the training data set to the validation data set, as seen by the validation accuracy of 93.8%.

Keywords: waste classification; waste data sets; work flow; efficient net raining.

DOI: 10.1504/IJIPT.2024.143756

International Journal of Internet Protocol Technology, 2024 Vol.17 No.1, pp.19 - 30

Accepted: 08 Jun 2024
Published online: 06 Jan 2025 *