Efficient E-waste Classification for Sustainable Recycling

The growing number of manufactured electrical and electronic devices has led to increased electronic waste (e-waste), including damaged, useless, or outdated electronic equipment.Effective e-waste management has become a global issue, and one way to address this problem is through machine learning techniques to classify e-waste and identify its most valuable components.In this paper, we deployed machine learning algorithms like random forest (RF), support vector machine (SVM), decision tree (DT), and k-nearest neighbors (KNN) comparing with deep learning algorithm "You Only Look Once" version 5 (YOLOv5) with the e-waste bin for image classification to identify e-waste and non-e-waste.The YOLOv5 with smart container uses features to extract relevant information from the images to classify each student input sample into e-waste or non-e-waste.Our results show that the YOLOv5 classifier achieved an accuracy of 90.32% in classifying the e-waste samples.