EMG-based human-machine interface system

Abstract

The paper presents an electromyographic based (EMG based) human-machine interface system. To retain a constraint-free user environment, EMG sensing is limited to three arm muscles. EMG signals are processed to attain parameters that are related to the muscles' temporal activities. Using these parameters, a unique signature is constructed for each particular gesture. The problem of gesture classification is carried out in a framework of statistical pattern recognition. Experimental investigation was carried out to examine the system's reliability in recognizing 12 arm gestures. The results show that the system can recognize the 12 gestures with a success rate of 96%.