A New Approach to Detection of Muscle Activation by Independent Component Analysis and Wavelet Transform
Recent works have demonstrated that the Independent Components (ICs) of simultaneously-recorded surface Electromyography (sEMG) recordings are more reliable in monitoring repetitive movements and better correspond with ongoing brain-wave activity than raw sEMG recordings. In this paper we propose to detect single muscle activation, when the arms reach a target, by means of ICs time-scale decomposition. Our analysis starts with acquisition of sEMG (surface EMG) signals; source separation is performed by a neural net-work that implements on Independent Component Analysis algorithm. In this way we obtain a signal set each representing single muscle activity. The wave-let transform, lastly, is utilised to detect muscle activation intervals.
KeywordsSurface EMG ICA
Unable to display preview. Download preview PDF.
- McKeown, M. J., Torpey, D. C., Gehm W. C.: Non-Invasive Monitoring of Functionally Distinct Muscle Activations during Swallowing. Clinical Neurophysiology (2002).Google Scholar