EEG Artifacts Removal Using A Modified Wavelet Enhanced Independent Component Analysis

To separate the clean EEG signals from noises and artifacts, it is necessary to do the cleaning process prior EEG signals can be used and analyzed. Many researches has been done to remove noises or artifacts and to obtain a clean EEG signal. Filtering and artifact removal are pre-processing steps commonly used to extract clean EEG data.A common method for artifact removal is ICA(Independent Component Analysis). Independent components(ICs) come from undesired sources that are mixed with the useful signal, and the assessment of such ICs allows them to be detected. But the removed ICs also can contain some useful information. To overcome this problem, wavelet-enhanced ICA(wICA) can be used, and this method applies a wavelet threshold for each wavelet coefficient to suppress abnormal deformation in each wavelet coefficient. However, the EEG signals are affected by various artifact components, and those that have the greatest influence are electromyography(EMG) and electrooculography(EOG). These artifacts may appear simultaneously, randomly or interruptedly, so a fixed threshold level is not really appropriate.Therefore, there are two main objectives in this research. First objective is to find the automatic method of identification of artifactual component that will help decrease the time consumed in ICA artifact removal. The second objective is to find the flexible thresholds that are needed to optimize the WT output of the EEG signal.