Wavelet-based envelope features with automatic EOG artifact removal: Application to single-trial EEG data

► Automatic EOG artifact removal is proposed to eliminate the EOG artifacts by means of ICA and correlation coefficient. ► The features are extracted from wavelet transform data by amplitude modulation method. ► The SVM is used for the discrimination of wavelet-based AM features. ► The proposed method compares with EEG data without EOG artifact removal, band power features and LDA classifier.