Automatic Removal of Ocular Artifact from EEG with DWT and ICA Method

Ocular artifact (OA) is one of the main interferences in electroencephalogram (EEG) recordings. It appears as a big pulse and has a strong impact to EEG signals. To overcome OA interference in EEG data, a novel automatic method of OA removal, denoted as DWICA, was proposed in this paper. In DWICA, the discrete wavelet transform (DWT) is applied to every recorded signal to obtain multiple scale coefficients. Then the independent component analysis (ICA) algorithm is used, and its input is the coefficients connected in series. Thus the independent components are acquired quickly in wavelet domain. The criterion of angle cosine is introduced to recognize ocular artifact, and the corresponding component is set to zero. Furthermore, the artifact free components are projected to original electrodes with inverse ICA algorithm. Finally, DWT is inversed to obtain the artifact free brain signals. Quantitative studies about suppression of OA distorting the underlying cerebral activity and accurate evaluation on denoising effect of DWICA are finished in this paper. Experiment results show that DWICA is preferable and effective in automatic OA correction. Meanwhile, DWICA is powerful in noise immunity and fast in convergence rate, and it provides a preferable method for EEG preprocessing on-line