Separation of P300 event-related potential using time varying time-lag blind source separation algorithm. (July 2017)

• Record Type: Journal Article
• Authors: Sabeti, Malihe; Boostani, Reza
• Is Part Of: Computer methods and programs in biomedicine. Volume 145(2017)
• Page Start: 95
• Page End: 102
• Publication Date: 2017-07
• Subjects: P300 component -- Blind source separation -- Schizophrenia; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2017.04.014
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: We analyzed P300 waveform of twenty schizophrenic patients and twenty age-matched healthy subjects. The P300 usually is extracted by averaging over time locked single-trial measurements assuming P300 does not vary much from trial to trial. Observation of variation in the P300 waveform permits the evaluation of dynamic changes in cognitive process. In this study, time varying time-lag source separation algorithm is used for separation of P300 waveform from the on-going background EEG. Our results over simulated and real data showed that the proposed scheme is suitable tool for dynamic estimation of P300 parameters. Abstract: Synchronous averaging over time locked single-trial of event-related potential (ERP) is known as the simplest scheme to extract P300 component. This method assumes the P300 features are invariant through the time while they are affected by factors like brain fatigue and habitation. In this study, a new scheme is proposed termed as time-varying time-lag blind source separation (TT-BSS) which is upon the second order statistics of signal to separate P300 waveform from the background electroencephalogram (EEG) while it captures the time variation of P300 component. The time-lag parameter for all channels is determined by maximizing the correlation (similarity) between two successive trials. As the time-lag parameter is varying by time (trial to trial), an average is taken over the time-lag covariance matrices of all two consecutive trials. TT-BSS finally estimates a transform (separating matrix) by joint diagnolization of the covariance matrix of trials and the averaged covariance matrix of the time varying time-lag. To assess the proposed scheme, synthetic and real EEGs containing P300 are used. The EEG signals were collected from twenty schizophrenic and twenty age-matched normal subjects via 20 channels through the resting state and in presence of the oddball audio stimulus. Empirical achievements over the simulated and real EEGs imply on the superiority of TT-BSS in dynamic estimation of P300 characteristics compared to state-of-the-art counterparts such as constant time-lag BSS, constrained BSS and synchronous averaging.