Key points are not available for this paper at this time.
ABSTRACT The rising challenges posed by electronic waste (e‐waste) to environmental and human health necessitate the advancement of smarter, faster, and more accurate e‐waste management solutions. Despite significant advancements in object detection technologies, current models often struggle with the real‐time classification of diverse e‐waste categories, limiting their practical application in large‐scale recycling operations. Addressing this gap, this paper introduces YOLO11 , a next‐generation real‐time object detection framework specifically optimized for the detection and classification of diverse e‐waste categories. Leveraging the power of deep learning, our model was trained on two distinct custom datasets, achieving remarkable classification accuracies of 99% and 98%, respectively. This study is among the first to demonstrate the real‐world applicability of the newly released YOLO11 architecture in the domain of e‐waste, showcasing its robustness and speed in diverse and cluttered environments. The system is capable of accurately detecting and classifying various categories of e‐waste in real‐time, offering a practical solution for automated sorting and collection processes. Through extensive experiments, the YOLO11 model achieved exceptional performance, achieving a recall of 0.968, mAP@ (Mean Average Precision) 0.5 of 0.992, and mAP@0.5–0.95 of 0.884 in all classes. Strong generalization and precise object recognition are shown by high class‐wise mAP@0.5–0.95 values, such as 0.991 for phone, 0.943 for keyboard, and 0.912 for laptop. The model is ideal for real‐time applications since it can identify a variety of e‐waste objects with a fast GPU‐based inference time (4.9 ms). The experimental findings show that YOLO11 is not only a significant advancement in the field of real‐time object detection but also a promising step toward smarter, more automated e‐waste management systems. By bridging AI innovation with environmental sustainability, the proposed work contributes to the urgent global effort to foster greener, more circular economies.
Biswas et al. (Sat,) studied this question.