Reproducibility of the identification process of stump muscle EMG in prosthetic gait by a dynamic recurrent neural network

摘要

Remaining muscle groups of the stump, pelvis and thorax seem to be sufficient to simulate locomotion movements of the prosthetic limb. Although, the identification process is less reproducible if the EMG signals are not directly linked to the mapped kinematics, the DRNN is able to reproduce the temporal aspects of gait, which justifies its application in intelligent prosthetic devices.