The study findings suggest sustainability as the most important criterion among the identified enablers for computer vision technology implementation in e-waste management.
Authors
Himanshu Sharma, Indian Institute of Management, Kashipur, U.S. Nagar, Uttarakhand, India.
Harish Kumar, Indian Institute of Management, Kashipur, U.S. Nagar, Uttarakhand, India.
Sachin Kumar Mangla, Full Professor and Director, Research Center for Digital Circular Economy for Sustainable Development Goals (DCE-SDG), Jindal Global Business School, O.P. Jindal Global University, Haryana, India.
Summary
Computer vision technology has led to a robust and reliable e-waste management system by automating and streamlining waste processing. Computer vision technology offers various benefits leading to sustainable improvements in e-waste management practices. It is expected that the adoption of computer vision technology will revolutionize the way processing is carried out in e-waste management by minimizing human intervention, processing time, and cost requirements.
India, an emerging economy, faces enormous challenges in efficiently managing and controlling the continuously growing amount of e-waste and its impact on the environment and society. Therefore, it is imperative to adopt computer vision technology to leverage its various benefits.
In this study, we identify and analyze the complex interrelationships between the enablers of computer vision technology in e-waste management. From an extensive literature review, fifteen enablers are identified and verified by domain experts before using an integrated “Interpretative Structural Modelling (ISM)” and “Decision-Making Trial and Evaluating Laboratory (DEMATEL)” methodology to visualize the causal relationships.
The study findings suggest sustainability as the most important criterion among the identified enablers for computer vision technology implementation in e-waste management. Other significant enablers are adaptability and reliability, cost reduction, quality control and safety management. The study’s findings will help waste management practitioners to design appropriate strategies for implementing computer vision in e-waste management and creating effective and automated e-waste processes.
Published in: Journal of Cleaner Production
To read the full article, please click here.
