DWT-BSS: Blind Source Separation applied to EEG signals by extracting wavelet transform’s approximation coefficients

Abstract The Electroencephalogram (EEG) signal is widely contaminated by a physiological artifact, such as muscle activity, heart rhythm, and eye movement. researcher has proposed number of methods to clean the EEG signal. A group these called Blind Source Separation (BSS). In this paper, we suggest an approach that combines BSS Discrete Wavelet Transform (DWT) algorithm, in order evaluate after applying them approximation coefficients extracted using DWT. aim work identify which algorithms, family wavelet at decomposition level, would provide excellent performance. We used Spearman Correlation Coefficient (SCC) rate our methods. technique performs best, evaluated SCC between generated component coefficient obtained from Horizontal EOG results, AMICA, obtains value 0.81 for levels 2 while symlet scales 7 11. With 0.70 use Daubechies scale 9 Coiflets 5 level 1, AMICA also best calculated separated recovered Vertical EOG. While employing symlets 5, 7, 8, 2, 3 when 1 2.