Hand gesture SEMG signal recognition based on ART2 neutral network
Jihai Yang · 2010
In view of the problems of efficiency and stability existing in hand gesture SEMG signal recognition,a method of hand gesture recognition based on the adaptive resonance neutral network 2 (ART2) was proposed. Compared with the back propagation (BP) network classifier,ART2 classifier effectively improves the recognition rate,reduces the signal processing time,and is not sensitive to individual differences in the single-user experiments conducted on eight classes of hand gestures for eight subjects. Multi-user experimental results also indicate that ART2 classifier has good adaptive capacity and stability in discriminating hand gesture SEMG signals.