Influence of the feature space on the estimation of hand grasping force from intramuscular EMG

Abstract

The study compares the performance of different combinations of nine features extracted from intramuscular electromyogram (EMG) recordings for the estimation of grasping force within the range 0-100% maximum voluntary contraction (MVC). Single-channel intramuscular EMG was recorded from the flexor digitorum profundus (FDP) muscle from 11 subjects who exerted three force profiles during power grasping. The ability of the features to estimate force with a 1st order polynomial (poly]) and an artificial neural network (ANN) model was assessed using the adjusted coefficient of determination (R-2). Willison amplitude (WAMP) and root mean square (RMS) showed the highest R-2 (similar to 0.88) values for poly]. The performance of all the features to predict force significantly increased (P < 0.01) when an ANN was applied. In this case, the Modified Mean Absolute Value (MMAV) demonstrated the best performance (similar to 0.91). The results showed that a single channel intramuscular EMG recording represents the entire grasping force range (0-100% MVC) measured from the FDP muscle. The association between EMG and force depends on the features extracted and on the model. (C) 2012 Elsevier Ltd. All rights reserved.