Classification of Ocular Artifacts in EEG Signals Using Hierarchical Clustering and Case-based Reasoning

Analysis of Electroencephalograms (EEG) recordings is becoming an important research area. However, if the signal is contaminated with noises or artifacts then it could mislead the diagnosis result. Therefore, it is important to remove artifacts from the EEG signal. This paper presents a classification approach to detect ocular artifact in the EEG signal. The proposed approach combines several methods i.e., case-based reasoning (CBR), Hierarchical clustering and Independent component analysis. The results show that the proposed system can classify EEG signal and ocular artifacts 95% accurately.