SEMG for Human Computer Interface Using ANN to Navigate Wheel Chair

This paper presents an approach to identify hand gestures with muscle activity separated from electromyogram (EMG) using Back Propagation analysis with the goal of using hand gestures for humancomputer interaction. While there are a number of previous reported works where EMG has been used to identify movement, the limitation of these works is that the systems are suitable for gross actions and when there is one prime-mover muscle involved. This paper reports overcoming the difficulty by using independent component analysis to separate muscle activity from different muscles and classified using back propagation neural networks. The experimental results show that the system was accurately able to identify the hand gesture using this technique (95%). The advantage of this system is that it is easy to train one to use it and can easily be implemented in real time. DOI: 10.4018/978-1-4666-1755-1.ch012