Age classification based on EMG signal using Artificial Neural Network

Age classification is a useful tool for creating an automatic system that can identify or verify and classify a person into an age group. In this paper a unique approach for classifying different aged people based on their forearm electromyography (EMG) signal, which has different characteristics from teenager to old is proposed. The Electromyography signal generates from the movement of brachioradialis muscle and antebrachial vein of lower portion of forearm as well as flexor carpi radialis tendon and flexor digitorum superficialis tendon of upper portion of wrist connected to forearm. In this study, various time and frequency domain features are extracted for analyzing motor unit recruitment with increased power of skeletal muscle and force produced by clenching muscles with maximum isometric contraction of the dominant forearm. The extracted time and time-frequency based features are used as the input vector for Artificial Neural Network (ANN) based classification to classify different aged subjects according to their age group from teenager to old. A backpropagation algorithm with three feed forward neural network is used for training and testing the classification. The results show that the accuracy of classifying different aged people according to corresponding age group is perfect and significant.