A.R.I.S.: Automated Recycling Identification System for E-Waste Classification Using Deep Learning

TL;DR

A.R.I.S. is a low-cost, portable deep learning-based system that improves e-waste classification and sorting efficiency, significantly enhancing material recovery in electronic waste recycling.

Contribution

The paper introduces A.R.I.S., a novel portable e-waste sorter using YOLOx for real-time classification, achieving high accuracy and low latency, advancing recycling technology.

Findings

90% overall precision in classification

82.2% mean average precision (mAP)

84% sortation purity

Abstract

Traditional electronic recycling processes suffer from significant resource loss due to inadequate material separation and identification capabilities, limiting material recovery. We present A.R.I.S. (Automated Recycling Identification System), a low-cost, portable sorter for shredded e-waste that addresses this efficiency gap. The system employs a YOLOx model to classify metals, plastics, and circuit boards in real time, achieving low inference latency with high detection accuracy. Experimental evaluation yielded 90% overall precision, 82.2% mean average precision (mAP), and 84% sortation purity. By integrating deep learning with established sorting methods, A.R.I.S. enhances material recovery efficiency and lowers barriers to advanced recycling adoption. This work complements broader initiatives in extending product life cycles, supporting trade-in and recycling programs, and reducing environmental impact across the supply chain.