Gesture based universal controller using EMG signals

Abstract

Electromyography (EMG) is a technique for evaluating and recording the electrical activity produced by skeletal muscles. An Electromyograph detects the electrical potential generated by muscle cells when these cells are electrically or neurologically activated. The signals can be analyzed to detect the biomechanics of human or animal movement. Measured EMG potentials range between less than 50 uV and up to 20 to 30 mV, depending on the muscle under observation. Through this paper we have aimed at developing a controller that uses muscle action to control the devices or gadgets that can help ease work of people (mostly aged adults). As a proof of concept we are working at deveoping a device that can run a robot. A specific movement of the arms can lead to varied voltage levels that can correspond to specific activities, which forms the basis of this project. The signals generated from the muscle are signal conditioned, filtered and sent to a micro-controller which compares it to an algorithm stored on-board. It is then wirelessly transmitted to the required device.