Institutions | About Us | Help | Gaeilge
rian logo

Go Back
Single-trial detection in EEG and MEG: Keeping it linear
Parra, Lucas C.; Alvino, Chris; Tang, Akaysha; Pearlmutter, Barak A.; Yeung, Nick; Osman, Allen; Sajda, Paul
Conventional electroencephalography (EEG) and magnetoencephalography (MEG) analysis often rely on averaging over multiple trials to extract statistically relevant di7erences between two or more experimental conditions. We demonstrate that by linearly integrating information over multiple spatially distributed sensors within a prede9ned time window, one can discriminate conditions on a trial-by-trial basis with high accuracy. We restrict ourselves to a linear integration as it allows the computation of a spatial distribution of the discriminating source activity. In the present set of experiments the resulting source activity distributions correspond to functional neuroanatomy consistent with the task (e.g. contralateral sensory-motor cortex and anterior cingulate).
Keyword(s): Computer Science; Hamilton Institute; Linear integration; High-density electroencephalography; EEG; Magnetoencephalography; MEG; Single-trial analysis; Brain–computer interface; BCI
Publication Date:
Type: Journal article
Peer-Reviewed: Yes
Institution: Maynooth University
Citation(s): Parra, Lucas C. and Alvino, Chris and Tang, Akaysha and Pearlmutter, Barak A. and Yeung, Nick and Osman, Allen and Sajda, Paul (2003) Single-trial detection in EEG and MEG: Keeping it linear. Neurocomputing, 52. pp. 177-183. ISSN 0925-2312
Publisher(s): Elsevier
File Format(s): other
Related Link(s):
First Indexed: 2020-01-31 06:14:53 Last Updated: 2020-04-02 07:00:10