Role of Internet of Things and Artificial Intelligence for electronic waste management: A Comprehensive Review and Recommendations

Electronic waste (e-waste) is one of the fastest-growing waste streams worldwide, driven by rapid technological change and increased consumption of electronic products. Improper management and disposal of e-waste lead to the release of hazardous materials, including heavy metals and toxic chemicals, posing significant challenges to environmental sustainability and human health. Recently, Industry 4.0-enabled technologies such as the Internet of Things (IoT), machine learning (ML), and deep learning (DL) have emerged as promising technologies for e-waste monitoring, classification, and environmental risk assessment. Although, recent studies have increasingly integrated multiple sensing modalities, where most existing methods are application-specific and rely on low-level integration of data from heterogeneous sources, without adopting a unified feature-level multimodal fusion approach for systematic real-time e-waste hazard assessment. This review presents a comparative analysis of IoT and AI implementation in e-waste management and identified key research gaps and the performance of these two technologies. The analysis shows that both technologies enhance waste monitoring, routing efficiency, and intelligent decision-making in e-waste management. Furthermore, AI-enabled methods have been shown to be successful at e-waste classification, hazard identification, and automated disassembly. Though recent research has begun to incorporate multiple sensing modalities, most AI–IoT studies have been application-specific, and a unimodal framework for full-scale real-time hazard assessment is still lacking. The gaps in the existing literature led to the conceptualization of an AI–IoT system that combines image-based waste classification, environmental sensing, and multimodal data fusion for real-time, intelligent detection of hazardous waste.