Smartphone-Based Tele-Rehabilitation System for Frozen Shoulder Using a Machine Learning Approach
Abstract
Frozen shoulder is a very painful condition that affects patients' daily life. Patients with frozen shoulder have to go to a hospital or medical center to get appropriate rehabilitation. Transportation to the hospital raises healthcare costs and the process can be time-consuming. We have developed a tele rehabilitation system which allows patients to perform an at-home exercise. According to our existing system, it is only available for high-end smartphones with multiple sensors that include accelerometer, gyroscope, and magnetic field sensors. In this work, we propose a novel approach using machine learning to estimate the arm angle of rotation using only the accelerometer sensor. Results show that reasonable accuracy can be obtained so that it may be used with lower-end Android smartphone devices that only have an accelerometer available. A web-based interface enables the medical practitioner such as a physiotherapist to monitor and administer an appropriate rehabilitation program for more effective recovery.
Authors: Kanmanus Ongvisatepaiboon, Jonathan H. Chan, Vajirasak Vanijja
Published in: IEEE Symposium Series on Computational Intelligence (SSCI) (2015)