Detection and classification of subject-generated artifacts in EEG signals using autoregressive models

• Published in: Journal of neuroscience methods Vol. 208; no. 2; pp. 181 - 189
• Main Authors: Lawhern, Vernon, Hairston, W. David, McDowell, Kaleb, Westerfield, Marissa, Robbins, Kay
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 15.07.2012
• Subjects: Autoregressive model; Blinking - physiology; Brain - physiology; Classification; EEG; Electroencephalography; Electroencephalography - methods; Electroencephalography - standards; Humans; Jaw - physiology; Models, Neurological; Nervous system; Reproducibility of Results; Signal Processing, Computer-Assisted - instrumentation; Support Vector Machine; Support vector machines; Support vector machines; Artifacts; Autoregressive model; Electroencephalography
• ISSN: 0165-0270; 1872-678X; 1872-678X
• DOI: 10.1016/j.jneumeth.2012.05.017

► We investigate the accurate detection and classification of subject-generated artifacts in continuous EEG recordings. ► Modeling of artifacts is performed using autoregressive (AR) modeling of artifact-contaminated EEG signals. Classification of EEG signals is performed using the support vector machine (SVM) classifier using the AR coefficients as features. ► Using the SVM classifier, we obtain accurate classification accuracy of a variety of artifacts (about 95%) across several subjects in our study. ► These results suggest that the AR coefficients can be used as features for classifying artifact-contaminated EEG segments. We examine the problem of accurate detection and classification of artifacts in continuous EEG recordings. Manual identification of artifacts, by means of an expert or panel of experts, can be tedious, time-consuming and infeasible for large datasets. We use autoregressive (AR) models for feature extraction and characterization of EEG signals containing several kinds of subject-generated artifacts. AR model parameters are scale-invariant features that can be used to develop models of artifacts across a population. We use a support vector machine (SVM) classifier to discriminate among artifact conditions using the AR model parameters as features. Results indicate reliable classification among several different artifact conditions across subjects (approximately 94%). These results suggest that AR modeling can be a useful tool for discriminating among artifact signals both within and across individuals.