Study of Myoelectric Prostheses Hand based on Independent Component Analysis and Fuzzy Controller

Recently, blind source separation (BSS) by independent component analysis (ICA) has received attention because of its potential in many signal processing fields. In this paper, ICA is applied to the electromyography (SEMG) signal analysis. One side, the experiment shows that ICA can decompose SEMG signal and separate source and noise effectively. On the other, after SEMG has been reconstructed, a method of Spectrum Coefficient is adopted and a fuzzy controller is designed specially to control the adjustment of myoelectric prosthetic hand´s movement. Many experiments show that some steady independent components always appear when muscle does the same tasks. This result will provide us with a promising method in the classification of muscle pattern recognition and the research on the Human-Computer Interface (HCI) technology.