Project Abstract

The motivation behind this work stems from the increasing need for precise and efficient tools to assess the effectiveness of physiotherapy exercises on the human skeletal system. This research positions itself uniquely at the intersection of physiotherapy, biomechanics, and data science. Unlike traditional methods that rely on subjective assessments or 2D data, our approach harnesses the power of 3D graph data analysis to offer a comprehensive evaluation of physio exercises. We captured 3D motion data of individuals performing selected physio exercises using motion capture technology. Statistical analyses were conducted to correlate these movements with exercise effectiveness and potential areas of improvement. Key findings from the analysis revealed distinct patterns in skeletal movements during different exercises. Certain exercises showed optimal alignment and joint mobility, while others highlighted areas of strain or imbalance. This research contributes a pioneering methodology for assessing physiotherapy exercises using 3D graph data analysis, filling a gap in current assessment tools that often lack precision and objectivity.

Keywords: Machine Learning, Computer Vision, Neural Networks

 Conference Details

Session: Poster Session B at Poster Stand 116

Location: Sir Stanley Clarke Auditorium at Wednesday 8th 09:00 – 12:30

Markers: Jay Morgan, Yuanbo Wu

Course: BSc Computer Science, 3rd Year

Future Plans: Other