Analysis and Classification of Multiple Hand Gestures using MMG Signals

Abstract

This research aimed to find out whether the MMG signal is useful in recognition of multiple hand gesture. The following hand gestures are Hand closing, wrist flexion, wrist extension, opening, pointing. MMG is reflects the intrinsic mechanical activity of muscle from the lateral oscillations of fibers during contraction. However, external mechanical noise sources such as movement artifact are known to cause considerable interference to MMG compromising the classification accuracy. First aim to develop various feature extraction algorithms software that can identify multiple hand gesture using MMG signal. The main purpose of this work is to identify the hand gestures that are predefined using the artificial neural network, which is particularly useful for classification purpose. The MMG patterns are extracted from the signals for each movement, the features extracted from the signals are given to the neural network for training and classification since it is the good technique for classifying the bio signals. The features like mean absolute value, root mean square, variance, standard deviation and root mean square are chosen to train the neural network.