A Novel Semi-Blind Signal Extraction Approach Incorporating Parafac for the Removal of Eye-Blink Artifact from EEGs

In this paper, a novel iterative blind signal extraction (BSE) scheme for the removal of the eye-blink artifact from electroencephalogram (EEC) signals is proposed. In this method, in order to remove the artifact, the signal extraction algorithm is provided with a priori information, i.e., an estimation of the column of the mixing matrix corresponding to the eye- blink source. The a priori knowledge, namely the vector corresponding to the spatial distribution of the eye-blink factor, is identified by using the method of parallel factor analysis (PARAFAC). Hence, we call the BSE approach, semi- blind signal extraction (SBSE). The results demonstrate that the proposed algorithm effectively identifies and removes the eye-blink artifact from raw EEC measurements.