SEMG based human computer interface for physically challenged patients

This paper present the use of hand gestures for human-computer interaction, this paper presents an approach to identify hand gestures using muscle activity separated from electromyogram (EMG) using ANN. To retain a constraint-free user's environment, EMG sensing is limited to three arm muscles. EMG signals are processed to attain parameters that are related to the muscles temporal activities. The attainment of these parameters through time constructs a unique signature for each particular gesture. Experimental investigation was carried out to examine the system's reliability in recognizing 6 arm gestures. The results show that the system can recognize the 6 gestures with a success rate of 98%. The advantage of such a system is that it is easy to train by a layer, and can easily be implemented in real time after the initial training.