Use of RBF neural network in EMG signal noise removal
WSEAS Transactions on Circuits and Systems
Design of adaptive filter using Jordan/Elman neural network in a typical EMG signal noise removal
Advances in Artificial Neural Systems
Hi-index | 0.00 |
When a muscle cannot maintain the sustained contraction against a certain force level, this situation points out the onset of muscle fatigue. In many bio-mechanical studies, it is pursued to determine the fatigue by using electromyography signals, but none of them is capable of characterizing the fatigue in a quantitative manner. The need for determination of a fatigue index from the point of view of quantitative evaluation is derived from the use in physiotherapy exercises. In this study, EMG signals are recorded from biceps and triceps muscles during isometric contraction from 12 healthy subjects. Then, median frequency, and temporal and spectral moments, which are characterizing features of EMG signals are calculated. It is concluded that using higher order temporal and spectral moments for determining the muscle fatigue improves the performance compared to using only change in the median frequency.