Independent Component Analysis to Remove ECG interference from Single Channel Electromyographic Signal

The electromyogram (EMG) is the signal reflecting the electrical activity from the skeletal muscular tissue and the electrocardiogram (ECG) is signal resulting from the electrical activity of the heart. Trunk EMG signals are often contaminated by the ECG. The ECG removal is a difficult task because there is a spectral overlapping between both ECG and EMG signals. In this work, the ECG interference was attenuated by using independent component analysis (ICA). In order to do that, the contaminated EMG was used together with a low-pass filtered version of it as input to the ICA algorithm. The proposed method was effective in removing the ECG from EMG signals, for both simulated and real signals.