Show simple item record

dc.contributor.authorVirta, Joni
dc.contributor.authorTaskinen, Sara
dc.contributor.authorNordhausen, Klaus
dc.date.accessioned2017-04-12T09:32:14Z
dc.date.available2017-04-12T09:32:14Z
dc.date.issued2016
dc.identifier.citationVirta, J., Taskinen, S., & Nordhausen, K. (2016). Applying fully tensorial ICA to fMRI data. In <em>Proceedings of 2016 IEEE Signal Processing in Medicine and Biology Symposium</em> (pp. 1-6). Institute of Electrical and Electronics Engineers. <a href="https://doi.org/10.1109/SPMB.2016.7846858">doi:10.1109/SPMB.2016.7846858</a>
dc.identifier.otherTUTKAID_72992
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/53586
dc.description.abstractThere are two aspects in functional magnetic resonance imaging (fMRI) data that make them awkward to analyse with traditional multivariate methods - high order and high dimension. The first of these refers to the tensorial nature of observations as array-valued elements instead of vectors. Although this can be circumvented by vectorizing the array, doing so simultaneously loses all the structural information in the original observations. The second aspect refers to the high dimensionality along each dimension making the concept of dimension reduction a valuable tool in the processing of fMRI data. Different methods of tensor dimension reduction are currently gaining popUlarity in literature, and in this paper we apply two recently proposed methods of tensorial independent component analysis to simulated task-based fMRI data. Additionally, as a preprocessing step we introduce a novel extension of PCA for tensors. The simulations show that when extracting a sufficiently large number of principal components, the tensor methods find the task signals very reliably, something the standard temporal independent component analysis (tICA) fails in.
dc.language.isoeng
dc.publisherInstitute of Electrical and Electronics Engineers
dc.relation.ispartofProceedings of 2016 IEEE Signal Processing in Medicine and Biology Symposium, ISBN 978-1-5090-6713-8
dc.subject.otherfunctional magnetic resonance imaging data
dc.subject.otherfMRI
dc.subject.otherdata
dc.titleApplying fully tensorial ICA to fMRI data
dc.typeconferenceObject
dc.identifier.urnURN:NBN:fi:jyu-201704031868
dc.contributor.laitosMatematiikan ja tilastotieteen laitosfi
dc.contributor.laitosDepartment of Mathematics and Statisticsen
dc.contributor.oppiaineTilastotiede
dc.type.urihttp://purl.org/eprint/type/ConferencePaper
dc.identifier.doi10.1109/SPMB.2016.7846858
dc.date.updated2017-04-03T12:15:05Z
dc.type.coarconference paper
dc.description.reviewstatuspeerReviewed
dc.format.pagerange1-6
dc.type.versionacceptedVersion
dc.rights.copyright© IEEE, 2016. This is a final draft version of an article whose final and definitive form has been published by IEEE. Published in this repository with the kind permission of the publisher.
dc.rights.accesslevelopenAccessfi


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record