Electromyograph Estimation of Wheelchair Operators Using Deep Learning
Shimpei Aihara, Ryusei Shibata, Ryosuke Mizukami, Takara Sakai, Akira Shionoya · 2022
Introduction: The Paralympic Games have been attracting attention due to the improvement in the competitiveness of sports competitions.Therefore, exercise analysis using myopotential, performance evaluation, and condition evaluation, among others, are being actively promoted to improve competitiveness.However, because of the limitations of physical actions and the discomfort associated with attaching electrodes, devices, and cables to the body, EMG is often used under controlled conditions [1].As a result, in this study, we developed a method for estimating myoelectric potential with a neural network using a video camera and an inertial sensor that can be used in a real-world competition setting.