Automatic removal of various artifacts from EEG signals using combined methods.

In this article, a novel and robust method is proposed to automatically remove various artifacts from EEG signals. First, canonical correlation analysis method is adopted to separate electromyography (EMG) artifacts from EEG signals. EMG-free EEG signals are obtained by subtracting the contribution of the components with autocorrelation value less than a threshold determined by the statistical analysis. For the removal of ocular artifacts, independent component analysis is applied to decompose the EMG-free signals. For the identification of eye movement artifact components, spectral and topographic features are extracted, and the classifier of support vector machine is used. Specifically, a peak detection algorithm of independent component is proposed to identify eye blink artifact components for the first time. The proposed artifact removal method is evaluated by the comparisons of EEG data before and after artifacts removal. The results show that the proposed method provides a promising method for complete artifact removal from EEG.