Welcome to the InfoSci Platform
Lower-Limb Rehabilitation at Home: A Survey on Exercise Assessment and Initial Study on Exercise State Identification Toward Biofeedback

Lower-Limb Rehabilitation at Home: A Survey on Exercise Assessment and Initial Study on Exercise State Identification Toward Biofeedback

Seanglidet Yean, Bu Sung Lee, Chai Kiat Yeo
Copyright: © 2020 |Volume: 12 |Issue: 1 |Pages: 13
ISSN: 1941-8663|EISSN: 1941-8671|EISBN13: 9781799806011|DOI: 10.4018/IJITN.2020010102
Cite Article Cite Article

MLA

Yean, Seanglidet, et al. "Lower-Limb Rehabilitation at Home: A Survey on Exercise Assessment and Initial Study on Exercise State Identification Toward Biofeedback." IJITN vol.12, no.1 2020: pp.15-27. http://doi.org/10.4018/IJITN.2020010102

APA

Yean, S., Lee, B. S., & Yeo, C. K. (2020). Lower-Limb Rehabilitation at Home: A Survey on Exercise Assessment and Initial Study on Exercise State Identification Toward Biofeedback. International Journal of Interdisciplinary Telecommunications and Networking (IJITN), 12(1), 15-27. http://doi.org/10.4018/IJITN.2020010102

Chicago

Yean, Seanglidet, Bu Sung Lee, and Chai Kiat Yeo. "Lower-Limb Rehabilitation at Home: A Survey on Exercise Assessment and Initial Study on Exercise State Identification Toward Biofeedback," International Journal of Interdisciplinary Telecommunications and Networking (IJITN) 12, no.1: 15-27. http://doi.org/10.4018/IJITN.2020010102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Aging causes loss of muscle strength, especially on the lower limbs, resulting in a higher risk of injuries during functional activities. To regain mobility and strength from injuries, physiotherapy prescribes rehabilitation exercise to assist the patients' recovery. In this article, the authors survey the existing work in exercise assessment and state identification which contributes to innovating the biofeedback for patient home guidance. The initial study on a machine-learning-based model is proposed to identify the 4-state motion of rehabilitation exercise using wearable sensors on the lower limbs. The study analyses the impact of the feature extracted from the sensor signals while classifying using the linear kernel of the support vector machine method. The evaluation results show that the method has an average accuracy of 95.83% using the raw sensor signal, which has more impact than the sensor fused Euler and joint angles in the state prediction model. This study will both enable real-time biofeedback and provide complementary support to clinical assessment and performance tracking.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.