TY - GEN
T1 - An EMG biofeedback device for video game use in forearm physiotherapy
AU - Converse, Hayes
AU - Ferraro, Teressa
AU - Jean, Daniel
AU - Jones, Laura
AU - Mendhiratta, Vikas
AU - Naviasky, Emily
AU - Par, Mang
AU - Rimlinger, Thomas
AU - Southall, Steven
AU - Sprenkle, Jason
AU - Abshire, Pamela
PY - 2013
Y1 - 2013
N2 - While electromyography (EMG) is widely used in experimental physiotherapy (PT), its use as a diagnostic aid and supplementary tool in clinical PT remains limited. We report an integrated, wireless PT system for the forearm, which registers muscle movements via EMG, records and wirelessly transmits the data to a laptop computer, and runs software to discriminate between arm motions. The next step is to interface with a custom video game which responds to user movement and provides real-time biofeedback to the user, allowing them to visualize whether they are performing their PT exercise properly. Our device incorporates existing technologies into a functional ensemble compatible with both at-home and clinical use. Current testing (n=7 subjects) indicates that the sensor is capable of discriminating between 6 classes of PT exercises with 92% accuracy (2 classes with 96% accuracy).
AB - While electromyography (EMG) is widely used in experimental physiotherapy (PT), its use as a diagnostic aid and supplementary tool in clinical PT remains limited. We report an integrated, wireless PT system for the forearm, which registers muscle movements via EMG, records and wirelessly transmits the data to a laptop computer, and runs software to discriminate between arm motions. The next step is to interface with a custom video game which responds to user movement and provides real-time biofeedback to the user, allowing them to visualize whether they are performing their PT exercise properly. Our device incorporates existing technologies into a functional ensemble compatible with both at-home and clinical use. Current testing (n=7 subjects) indicates that the sensor is capable of discriminating between 6 classes of PT exercises with 92% accuracy (2 classes with 96% accuracy).
UR - https://www.scopus.com/pages/publications/84893922126
U2 - 10.1109/ICSENS.2013.6688474
DO - 10.1109/ICSENS.2013.6688474
M3 - Conference contribution
AN - SCOPUS:84893922126
SN - 9781467346405
T3 - Proceedings of IEEE Sensors
BT - IEEE SENSORS 2013 - Proceedings
PB - IEEE Computer Society
T2 - 12th IEEE SENSORS 2013 Conference
Y2 - 4 November 2013 through 6 November 2013
ER -