Machine Learning in Reducing E-Waste

Abstract

E-waste is a waste which is gathered from various sources, Household sector is considered as a biggest source of generation of e-waste. E-waste consists of various components characterized as hazardous and non-hazardous components also contain approximately 1000 substances categorized in this category. E-waste is comprising of ferrous and non-ferrous metals ceramics and other items. When e-waste gets dismantled and continuously processed it jeopardizes the health environment, and surroundings. E-waste is a composition of bio accumulative and toxic substances containing like chromium, mercury, and toxic substances (Arora et al., 2024). Machine learning plays a very important role in regulating e-waste. In context to urban segments, week by week e-waste is calculated through building a prescient model, by building and creating gradient boosting regression tree (GBRT) and neutral network machine learning calculations. By incorporating machine learning, calculations will provide exact accurateness of algorithm. A convolutional neural network was created to bifurcate e-waste into different countries. These categories are as follows: cell phone, remote controller, battery, and light bulb.