Classification of sEMG Signals for Muscle Fatigue Detection Using Support Vector Machines
Reza Boostani; Fariba Biyouki; Saeed Rahati; Katri Laimi; Afsane Zadnia
https://urn.fi/URN:NBN:fi-fe2021042714980
Tiivistelmä
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 self- perceived fatigue. The aim of this study was to discriminate between fatigue and nonfatigue stages using support vector machine (SVM) approach. Thus, electromyographic (EMG) signals collected in the department of biomedical engineering of Islamic Azad university of Mashhad, were used. 10 features in time, frequency and time- scale domains were extracted from sEMG signals and the effect of different objective functions for dimensionality reduction and different SVM were evaluated for fatigue detection. The best accuracy (89.45%) was achieved through RBF kernel with ROC criterion while the best accuracy through linear SVM was 54.42%. These results suggest that the selected features contained some information that could be used by the nonlinear SVM with RBF kernel to best discriminate between fatigue and nonfatigue stages.
Kokoelmat
- Rinnakkaistallenteet [19207]