Removal of ECG artifacts from EEG using ICA

Abstract

The Independent component analysis (ICA) in Blind source separation (BSS) is introduced. A fast ICA algorithm is proposed. In contrast to most blind source separation algorithms, the method does not need to calculate higher order statistics. A pre-whiten procedure is performed to de-correlating the sensor signals before extracting vector. The proposed method is used to remove the ECG artifacts from clinical EEG signals successfully.