Deep Learning for Effective Electronic Waste Management and Environmental Health

Author:

Oise Godfrey Perfectson1ORCID,Susan Konyeha1

Affiliation:

1. University of Benin

Abstract

Abstract

Creating an advanced deep learning methodology for efficient management of electronic waste (e-waste) and preservation of environmental health is the aim of this research. The research tackles the growing problem of e-waste by compiling and preprocessing various datasets of e-waste images using a Sequential Neural Network (SNN) with TensorFlow and Keras. To improve the model's performance, this all-inclusive approach uses image augmentation techniques. In this work, efforts have been made to enhance the performance and computational efficiency of deep learning classifiers using hyperparameters. The study utilized e-waste data obtained from standard online repositories. The hyperparameter tuned modified CNN-based Sequential Neural Network model achieved an accuracy of 87%, precision of 87%, recall of 86% and f1_score of 86%. This model's strong performance highlights its real-time application potential and ease of integration into current e-waste management workflows. The suggested system is ready for widespread implementation and offers substantial advantages for environmental sustainability and resource conservation. This deep learning system helps reduce health risks associated with improper e-waste disposal, while also supporting ecological preservation by enabling the efficient sorting and classification of e-waste. The innovation resides in its capacity to streamline and automate the management of e-waste, offering a viable resolution to one of the most urgent environmental problems. This study is an excellent example of how cutting-edge artificial intelligence technologies can be integrated to improve waste management systems, giving global environmental health initiatives a scalable and useful tool.

Publisher

Springer Science and Business Media LLC

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3