A.R.I.S.: Automated Recycling Identification System for E-Waste Classification Using Deep Learning
2026-02-19 • Machine Learning
Machine Learning
AI summaryⓘ
The authors designed a small, affordable machine called A.R.I.S. that can quickly sort tiny pieces of electronic waste into metals, plastics, and circuit boards. It uses a smart computer program named YOLOx to recognize and separate these materials accurately in real time. Their tests showed the system sorts with about 90% precision and helps improve recycling by reducing lost resources. This approach supports better recycling and environmental care by making it easier to recover valuable materials.
electronic recyclingmaterial sortingYOLOxdeep learninginference latencyprecisionmean average precisioncircuit boardsresource recoveryautomated sorting
Authors
Dhruv Talwar, Harsh Desai, Wendong Yin, Goutam Mohanty, Rafael Reveles
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.