Space-by-time non-negative matrix factorization for single-trial decoding of M/EEG activity

Delis, I., Onken, A., Schyns, P. G. , Panzen, S. and Philiastides, M. (2016) Space-by-time non-negative matrix factorization for single-trial decoding of M/EEG activity. NeuroImage, 133, pp. 504-515. (doi: 10.1016/j.neuroimage.2016.03.043) (PMID:27033682) (PMCID:PMC4907687)

[img]
Preview
Text
118013.pdf - Published Version
Available under License Creative Commons Attribution.

1MB

Abstract

We develop a novel methodology for the single-trial analysis of multichannel time-varying neuroimaging signals. We introduce the space-by-time M/EEG decomposition, based on Non-negative Matrix Factorization (NMF), which describes single-trial M/EEG signals using a set of non-negative spatial and temporal components that are linearly combined with signed scalar activation coefficients. We illustrate the effectiveness of the proposed approach on an EEG dataset recorded during the performance of a visual categorization task. Our method extracts three temporal and two spatial functional components achieving a compact yet full representation of the underlying structure, which validates and summarizes succinctly results from previous studies. Furthermore, we introduce a decoding analysis that allows determining the distinct functional role of each component and relating them to experimental conditions and task parameters. In particular, we demonstrate that the presented stimulus and the task difficulty of each trial can be reliably decoded using specific combinations of components from the identified space-by-time representation. When comparing with a sliding-window linear discriminant algorithm, we show that our approach yields more robust decoding performance across participants. Overall, our findings suggest that the proposed space-by-time decomposition is a meaningful low-dimensional representation that carries the relevant information of single-trial M/EEG signals.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Delis, Dr Ioannis and Schyns, Professor Philippe and Philiastides, Professor Marios
Authors: Delis, I., Onken, A., Schyns, P. G., Panzen, S., and Philiastides, M.
College/School:College of Medical Veterinary and Life Sciences > School of Psychology & Neuroscience
Journal Name:NeuroImage
Publisher:Elsevier
ISSN:1053-8119
ISSN (Online):1095-9572
Published Online:24 March 2016
Copyright Holders:Copyright © 2016 The Authors
First Published:First published in Neuroimage 133:504-515
Publisher Policy:Reproduced under a Creative Commons License

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

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
607901VISUALISEStefano PanzeriEuropean Commission (EC)600954RI NEUROSCIENCE & PSYCHOLOGY
653861Spatiotemporal characterization of value judgments and reward processing in the human brainMarios PhiliastidesBiotechnology and Biological Sciences Research Council (BBSRC)BB/J015393/2INP - CENTRE FOR COGNITIVE NEUROIMAGING
654411Neural correlates of learning and confidence during decision making and their utility in developing "intelligent technologies".Marios PhiliastidesEconomic & Social Research Council (ESRC)ES/L012995/1INP - CENTRE FOR COGNITIVE NEUROIMAGING
698281Brain Algorithmics: Reverse Engineering Dynamic Information Processing Networks from MEG time seriesPhilippe SchynsWellcome Trust (WELLCOME)107802/Z/15/ZINP - CENTRE FOR COGNITIVE NEUROIMAGING