Eeg artifact removal techniques: A comparative study

Abstract

An Electroencephalograph (EEG) is widely used to study the working of brain. The main challenge in dealing with such signals is its non-stationary nature and high dimensionality. The propagation of signals from one electrode to other gives rise to presence of artifacts in the data. This can lead to generation of false results while working on the data. Ocular, Muscular, and Cardiac are some of the very common artifacts for a dataset dedicated for motor imagery classification. This paper deals with the techniques and their comparative analysis for removal of ocular artifact from EEG signals. On the basis of dataset, the paper shows a study of how Linear Regression, Filtering, and Independent Component Analysis(ICA) works on the removal of ocular artifact in this data. To verify the effect of artifact removal technique features were extracted from the data, before and after applying different techniques and further fed to the classifier. An improvement in the accuracy of motor imagery classification is observed when we apply various techniques of artifact removal. ICA proves to remove the artifacts most efficiently as compared to the other two techniques on this dataset. Precision, Recall, and F1-Score values are also determined for the comparative analysis.