Geometric Features based Muscle Fatigue Analysis using Low Frequency Band in Surface Electromyographic signals

In this study, an attempt has been made to evaluate the applicability of geometric features extracted from the different frequency bands of surface electromyography (sEMG) signals for detecting muscle fatigue condition. For this purpose, sEMG signals are acquired from twenty-five healthy volunteers during isometric contraction of biceps brachii muscle. The nonfatigue and fatigue segments are obtained from preprocessed signals and are separated into low frequency band (LFB: 15- 45Hz), medium frequency band (MFB: 55-95Hz) and high frequency band (HFB: 95-500Hz). The analytical representations of these signals are obtained from Hilbert Transform and the features, area and perimeter are extracted from the resultant shape. The results demonstrate that the features obtained from the three bands can differentiate nonfatigue and fatigue conditions with significant difference (p<0.05). Among the three bands, LFB achieves high sensitivity of 88% and 84% for perimeter and area feature respectively. However, sensitivity in MFB and HFB is decreased for both the features. It appears that the geometric features associated with LFB signals are more sensitive in detecting fatigue. It is interesting to note that the sensitivity is in acceptable level for low-frequency signals (15- 45Hz). However, the study has to be conducted on large population to draw a reliable conclusion.