Myoelectric prosthetic hands serve as assistive devices to improve the quality of life for amputees. Recently, there has been a growing demand for control systems with higher degrees of freedom and continuous motion capabilities. In this study, we propose a real-time control system employing a neural network, TF2AngleNet, which estimates finger joint angles from five-channel surface electromyography (sEMG) signals to infer the user’s motion intent. To validate the effectiveness of the proposed system, evaluation experiments were conducted with healthy participants. Future work will focus on developing real-time fine-tuning methods to enhance adaptability to temporal variations and individual differences.
Jiang et al. (Wed,) studied this question.