-
Limb Position Tolerant Pattern Recognition for Myoelectric Prosthesis Control with Adaptive Sparse Representations from Extreme Learning
Classification algorithms used to predict intended movements of an amputee for upper-limb prosthesis control using EMG signals must tolerate changes in limb position and loads which affect those signals. Extreme Adaptive Sparse Representation Classification (EASRC) significantly outperforms other classification methods in untrained upper-limb positions, and the performance is achieved from less user training.