Across-subjects classification of stimulus modality from human MEG high frequency activity

Westner, B. U., Dalal, S. S., Hanslmayr, S. and Staudigl, T. (2018) Across-subjects classification of stimulus modality from human MEG high frequency activity. PLoS Computational Biology, 14(3), e1005938. (doi: 10.1371/journal.pcbi.1005938) (PMID:29529062) (PMCID:PMC5864083)

223179.pdf - Published Version
Available under License Creative Commons Attribution.



Single-trial analyses have the potential to uncover meaningful brain dynamics that are obscured when averaging across trials. However, low signal-to-noise ratio (SNR) can impede the use of single-trial analyses and decoding methods. In this study, we investigate the applicability of a single-trial approach to decode stimulus modality from magnetoencephalographic (MEG) high frequency activity. In order to classify the auditory versus visual presentation of words, we combine beamformer source reconstruction with the random forest classification method. To enable group level inference, the classification is embedded in an across-subjects framework. We show that single-trial gamma SNR allows for good classification performance (accuracy across subjects: 66.44%). This implies that the characteristics of high frequency activity have a high consistency across trials and subjects. The random forest classifier assigned informational value to activity in both auditory and visual cortex with high spatial specificity. Across time, gamma power was most informative during stimulus presentation. Among all frequency bands, the 75 Hz to 95 Hz band was the most informative frequency band in visual as well as in auditory areas. Especially in visual areas, a broad range of gamma frequencies (55 Hz to 125 Hz) contributed to the successful classification. Thus, we demonstrate the feasibility of single-trial approaches for decoding the stimulus modality across subjects from high frequency activity and describe the discriminative gamma activity in time, frequency, and space.

Item Type:Articles
Additional Information:This work was supported by ERA-Net NEURON via the German Federal Ministry of Education and Research,, grant 01EW1307, to SSD; European Research Council,, Starting Grant 640488, to SSD; Deutsche Forschungsgemeinschaft,, Emmy Noether Programme Grant HA 5622/1-1, to SH; European Research Council,, Consolidator Grant 647954, to SH; Wolfson Foundation and Royal Society,, to SH; and European Union’s Horizon 2020,, 661373, to TS.
Glasgow Author(s) Enlighten ID:Hanslmayr, Professor Simon
Creator Roles:
Hanslmayr, S.Funding acquisition, Resources, Writing – review and editing
Authors: Westner, B. U., Dalal, S. S., Hanslmayr, S., and Staudigl, T.
College/School:College of Medical Veterinary and Life Sciences > School of Psychology & Neuroscience
Journal Name:PLoS Computational Biology
Publisher:Public Library of Science
ISSN (Online):1553-7358
Published Online:12 March 2018
Copyright Holders:Copyright © 2018 Westner et al.
First Published:First published in PLoS Computational Biology 14(3): e1005938
Publisher Policy:Reproduced under a Creative Commons License
Data DOI:10.17605/OSF.IO/M25N4

University Staff: Request a correction | Enlighten Editors: Update this record