This paper presents the design and fabrication of a textile-based soft Electromyography (EMG) sensor and machine-learning-based methods to detect muscle spasticity. The textile EMG sensor is flexible, foldable, stretchable, washable for multiple times, and easily customizable to meet the heterogeneous needs of SCI individuals. The machine learning algorithms that can estimate the muscle status and the performance of functional ADLs by classification of function ADLs and the detection of muscle spasticity. The soft textronic sensors, its intelligent machine learning algorithms, and biofeedback-based rehabilitation has the potential to enable home-based rehabilitation and encourage more manipulation for function ADLs and independence in SCI and stroke individuals.
Soft Physiology Sensors and Machine Learning to Enhance Spinal Cord Injury and Stroke Rehabilitation Outcomes in Home Settings
- Views Icon Views
- PDF LinkPDF
- Share Icon Share
- Search Site
Huang, T, Yang, J, Pushaj, E, Silvanov, V, Yu, S, Yang, X, Su, H, Chang, S, & Francisco, G. "Soft Physiology Sensors and Machine Learning to Enhance Spinal Cord Injury and Stroke Rehabilitation Outcomes in Home Settings." Proceedings of the 2019 Design of Medical Devices Conference. 2019 Design of Medical Devices Conference. Minneapolis, Minnesota, USA. April 15–18, 2019. V001T05A001. ASME. https://doi.org/10.1115/DMD2019-3267
Download citation file: