The extraction of critical raw materials (CRMs) from waste printed circuit boards (WPCBs) represents a crucial challenge for the economy, particularly in the electronics sector. To improve the concentration of individual CRMs and facilitate their extraction from WPCBs, we propose an innovative approach based on machine learning and computer vision to guide mechatronics system in selectively disassembling various types of electronic components from WPCBs. Our approach addresses the need for a robust and automated solution to identify and localize valuable components that contain CRMs. Specifically, we use YOLOv5 and YOLOv8 models, which are the state of the art convolutional neural networks (CNN) for detection and localization tasks. Our pipeline, called EC-Det, starts from collecting a custom image set called V-PCB, and obtains a large collection of 10,829 high-quality images of WPCBs. These images are used to train the YOLO family variants which show excellent accuracy. Furthermore, we consider not only accuracy but also memory usage, training time, and inference time for our CNN models, evaluating their suitability for resource-constrained on the edge systems. Our results show that integration of machine vision system provides a highly effective and reproducible solution for guiding automated mechatronics system, thereby enhancing the efficiency of the CRMs extraction process.

Copy @article{mohsin2026extraction, author={Mohsin, Muhammad and Rovetta, Stefano and Masulli, Francesco and Cabri, Alberto}, journal={IEEE Access}, title={Extraction of Critical Raw Materials From Waste Printed Circuit Boards Using Machine Learning and Computer Vision}, year={2026}, volume={14}, pages={50230--50245}, doi={10.1109/ACCESS.2026.3679216} }

Hepatopancreatic tumors present a critical imaging diagnostic challenge due to varying structures and sizes. This systematic review synthesizes recent developments in artificial intelligence and deep learning methods specifically targeted toward automated segmentation of hepatopancreatic tumors. We review state-of-the-art CNNs and visual transformers (ViTs), contrast dataset benchmarks, and discuss research challenges including pixel imbalances and clinical workflow deployment obstacles.

Copy @article{hussain2026systematic, title={A Systematic Review of Deep Learning Approaches for Hepatopancreatic Tumor Segmentation}, author={Hussain, R and Mohsin, Muhammad and Khan, D and Zohaib, M}, journal={Journal of Imaging}, year={2026}, publisher={MDPI} }

Transitioning to a circular economy is necessary to mitigate raw materials depletion. This paper investigates artificial intelligence's paradigm-shifting capabilities for optimizing product lifecycles, resource management, sorting efficiency, and waste valuation. By reviewing automated supply chains and disassembly mechanisms, we highlight how AI acts as an enabler for industrial resource efficiency.

Copy @article{mohsin2026transition, title={Transition Towards a Circular and Resource-Efficient Economy: An Artificial Intelligence Perspective}, author={Mohsin, Muhammad and Rovetta, Stefano and Masulli, Francesco and Cabri, Alberto}, journal={Applied Sciences}, year={2026}, publisher={MDPI} }

Zero Trust Architecture (ZTA) has emerged as a cornerstone in securing enterprise networks under the 'never trust, always verify' paradigm. This review provides a comprehensive analysis of ZTA implementation patterns, engineering challenges, deployment paradigms across cloud, IoT, and industrial networks, and addresses the open research questions in trust score optimization.

Copy @article{mushtaq2025systematic, title={A Systematic Literature Review on the Implementation and Challenges of Zero Trust Architecture Across Domains}, author={Mushtaq, Sadaf and Mohsin, Muhammad and Mushtaq, Muhammad Mujahid}, journal={Sensors}, volume={25}, number={19}, pages={6118}, year={2025}, publisher={MDPI} }

Waste-Printed Circuit Boards (WPCBs) are complex and contain critical raw materials alongside toxic elements. This paper reviews key advancements in AI applications for WPCB recycling, including computer vision systems for component detection, automated robotic systems, sorting classification models, and highlights how deep learning boosts recovery yields.

Copy @article{mohsin2025artificial, title={Artificial Intelligence Approach for Waste-Printed Circuit Board Recycling: A Systematic Review}, author={Mohsin, Muhammad and Rovetta, Stefano and Masulli, Francesco and Cabri, Alberto}, journal={Computers}, volume={14}, number={8}, pages={304}, year={2025}, publisher={MDPI} }

Robotic disassembly requires low-latency processing of video feeds to identify electronic elements. This paper outlines an edge computing and IoT infrastructure framework to process deep learning object detection models directly on-site, decreasing latency, data transmission overheads, and enabling real-time robotic interaction.

Copy @article{mohsin2025automatic, title={Automatic Disassembly of Waste Printed Circuit Boards: The Role of Edge Computing and IoT}, author={Mohsin, Muhammad and Rovetta, Stefano and Masulli, Francesco and Cabri, Alberto}, journal={Computers}, volume={14}, number={2}, pages={62}, year={2025}, publisher={MDPI} }

A system and database model for automated recognition, segmentation, and selective sorting of components on printed circuit boards (PCBs). Utilizes multi-modal convolutional networks trained to identify critical raw materials (CRMs) on recycling conveyor belts, facilitating robotic disassembly.