Paper Accepted at 15th International Conference on Intelligent Human-Computer Interaction, South Korea

We are happy to announce that one of our papers, “An Integrated System for Stroke Rehabilitation Exercise Assessment using KINECT v2 and Machine Learning, “ has been accepted and presented at the “15th International Conference on Intelligent Human-Computer Interaction, South Korea”. This work is an outcome of a CCDS project on “Automated and Computerized Rehabilitation Systems for Stroke Patients”. This work is jointly supervised by CCDS professors Dr. M Ashraful Amin, Dr. Amin Ahsan Ali, Dr. A K M Mahbubur Rahman, and Dr. Ashraful Islam and collaborated with Eshtiak Ahmed from Tampere University, Finland.

In this work, a home-based rehabilitation system is designed to address these challenges by leveraging the capabilities of the KINECT v2 3D camera. Our system, equipped with a graphical user interface (GUI), allows patients to perform, monitor, and record their exercises. By utilizing advanced machine learning algorithms, specifically G3D and disentangled multi-scale aggregation schemes, the system can analyze exercises, generating both primary objective (PO) and control factor (CF) scores out of 100.