Automatic EEG Artifact Removal: A Weighted Support Vector Machine Approach With Error Correction

• Published in: IEEE transactions on biomedical engineering Vol. 56; no. 2; pp. 336 - 344
• Main Authors: Shao, Shi-Yun, Shen, Kai-Quan, Ong, Chong Jin, Wilder-Smith, Einar P. V.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2009; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artifact removal; Artificial Intelligence; Blinking; Brain; Diagnostic Errors; Electrocardiography; electroencephalogram; Electroencephalography; Electroencephalography - methods; Error correction; Eyes; Heart; Humans; Independent component analysis; Mechanical engineering; Models, Cardiovascular; Muscles; Reproducibility of Results; Signal Processing, Computer-Assisted; Support vector machine classification; Support vector machines; weighted support vector machine (SVM)
• ISSN: 0018-9294; 1558-2531
• DOI: 10.1109/TBME.2008.2005969

An automatic electroencephalogram (EEG) artifact removal method is presented in this paper. Compared to past methods, it has two unique features: 1) a weighted version of support vector machine formulation that handles the inherent unbalanced nature of component classification and 2) the ability to accommodate structural information typically found in component classification. The advantages of the proposed method are demonstrated on real-life EEG recordings with comparisons made to several benchmark methods. Results show that the proposed method is preferable to the other methods in the context of artifact removal by achieving a better tradeoff between removing artifacts and preserving inherent brain activities. Qualitative evaluation of the reconstructed EEG epochs also demonstrates that after artifact removal inherent brain activities are largely preserved.