Apurba Roy is a Research Assistant at the AVIS Research Lab and an MSc student in Robotics and Mechatronics Engineering at the University of Dhaka. His research focuses on Explainable Artificial Intelligence (XAI), computer vision, medical image processing, and human-robot interaction.
His undergraduate thesis, titled “Enhancing Histology Cancer Cell Detection: Deep Learning Model Interpreted with Explainable AI (XAI) for Microscopic Tissue Image Analysis”, was supervised by Dr. Md Mehedi Hasan. The research explored the application of deep learning and explainability methods to improve transparency and interpretability in automated cancer cell detection.
His technical experience includes developing deep learning models for medical image analysis and applying Grad-CAM, LIME, and SHAP to explain model predictions. He has benchmarked object detection architectures, including YOLOv8, RetinaNet, and Faster R-CNN, and developed real-time gesture-controlled systems using embedded platforms and humanoid robots.
Beyond his academic research, Apurba has mentored teams participating in the Bangladesh Robot Olympiad (BdRO).
Research Interests
Computer Vision, Explainable AI (XAI), Deep Learning for Medical Imaging, UAV-based Agricultural Sensing, and Human-Robot Interaction.