Quantification of sEMG signals for automated muscle fatigue detection using nonlinear SVM

Abstract

<p>Fatigue is a multidimensional and subjective concept and is a complex phenomenon including various causes, mechanisms and forms of manifestation. Thus, it is crucial to delineate the different levels and to quantify selfperceived fatigue. The aim of this study was to introduce a method for automatic quantification and detection of muscle fatigue using surface EMG signals. Thus, sEMG signals from right sternocleidomastoid muscle of 9 healthy female subjects were recorded during neck flexion endurance test in Quaem hospital. Then six features in time, frequency and time- scale domains were extracted from signals. After dimensionality estimation and reduction, the SVM classifier was applied to the resulted feature vector. Then, the performance of linear SVM and nonlinear SVM with RBF kernel and the effect of show that the best accuracy is achieved using RBF kernel SVM with features using LLE criterion, were RMS, ZC and AIF. These results suggest that the selected features contained some information that could be used by nonlinear SVM with RBF kernel to best discriminate between fatigue and nonfatigue stages.</p>

<p> </p>

<p> </p>