Feature Analysis for Classification of Physical Actions Using Surface EMG Data

Based on recent health statistics, there are several thousand people with limb disability and gait disorders that require medical assistance. A robot assisted rehabilitation therapy can help them recover and return to a normal life. In this scenario, a successful methodology is to use an EMG signal based information to control the support robotics. For this mechanism to function properly, the EMG signal from the muscles has to be sensed and then the biological motor intention has to be decoded and finally the resulting information has to be communicated to the controller of the robot. An accurate understanding of the motor intention requires a pattern recognition based framework. Hence in this paper, we propose an improved classification framework through identification of the relevant features that drive the pattern recognition algorithm. Major contributions include a set of modified spectral moment based features and another relevant inter-channel correlation feature that contribute to an improved classification performance. Next, we conducted a sensitivity analysis of the classification algorithm to different EMG channels. Finally, the classifier accuracy with probabilistic neural networks based classifier is 92.7% and with an ensemble of subspace K-nearest neighbors algorithm it is 93.9% and is better than that of the other state of the art algorithms.