E-Waste Intelligent Robotic Technology (EIRT): A Deep Learning approach for Electronic Waste Detection, Classification and Sorting

Abstract

In nowadays world, electronic waste (e-waste) has become one of the leading and most present type of waste in the world, posing various environmental and health problems, hence becoming a problem that can no longer be ignored. In this paper we propose a deep learning-based approach in order to accomplish detection, classification and sorting of e-waste. Such approach has been named EIRT, standing for E-waste Intelligent Robotic Technology, and it consists of a classification algorithm, which will be used for the classification and of the e-waste, and a car equipped with a robotic arm, which will be used to move around within a certain area detecting, collecting and sorting the e-waste accordingly. The algorithm was written based on the EfficientNet-D2 architecture, having achieved an 82.32% of accuracy.