Automatic Removal of Ocular Artifacts from EEG Signals
Junfeng Gao, Chongxun Zheng, Pei Wang · 2009
Electroencephalogram (EEG) signals are often contaminated by ocular artifacts. In present study, a novel and robust technique is presented to eliminate ocular artifacts from EEG signals automatically. Independent component analysis (ICA) method is used to decompose EEG signals. In the first step, the features of topography and power spectral density of those components are extracted. In the second step, we introduce manifold learning algorithm to reduce the dimensionality of initial features. Then, a classifier is used to identify ocular artifacts components. The classifier is selected from several typical classifiers by comparing their classification performances. Classification results show that manifold learning with the nearest neighbor algorithm performs best. Finally, using an example of ocular artifacts removal, we show that the novel technique can effectively remove ocular artifacts with little distortion of underlying brain signals.