•  
  •  
 

Abstract

Prosthetic limbs hold a promise to renew the quality of life for the amputee. Neural commands are decoded via a classifier to generate control signals for the prosthetic devices. In the literature, many challenges and limitations have been identified that affect the prosthesis operation. One such drawback is muscle fatigue which degrades the surface electromyogram (sEMG) signals, and consequently, the performance of the deployed classification algorithm declines from 90% to 50% of average accuracy. We used a new technique using the Linear Discrimination Analysis (LDA) algorithm and the muscle synergy-based task discrimination (MSD) algorithm to improve the classification accuracy. In this technique, during muscles contraction/fatigue, we used the LDA algorithms in the beginning and the MSD algorithms later. The applied technique exhibited better movement classification performance during normal and muscle fatigue conditions. However, more work needs to be done to effectively solve the muscle fatigue problem in prosthesis design.

Share

COinS