Towards classifier visualisation in 3D source space

dc.contributor.authorKrol, Laurens R.
dc.contributor.authorMousavi, Mahta
dc.contributor.authorDe Sa, Virginia
dc.contributor.authorZander, Thorsten O.
dc.date.accessioned2021-01-06T12:28:59Z
dc.date.available2021-01-06T12:28:59Z
dc.date.issued2019-01-17
dc.description.abstractIn the context of brain-computer interfacing, it is important to investigate what regions of the brain a classifier focuses on. For one, this will clarify to what extent the classifier relies on brain activity, as opposed to undesirable non-cortical signals. More generally, the practice is informative as it allows conclusions to be drawn about the cortical regions-and thus, cortical functions-that contribute to the effect under investigation. In this study, we start to investigate different methods to visualise the regions of interest of classifiers based on windowed means and on common spatial patterns. Specifically, we take individually reconstructed source spaces and transform the classifier filter weights into relevance weights indicating the relative contribution of each source to the classifier. This is visualised across participants in an average brain. By decomposing the classifier weights into separate sources and localising these in the brain, this method provides a tool to evaluate classifiers and test hypotheses.en
dc.identifier.eissn2577-1655
dc.identifier.isbn978-1-5386-6650-0
dc.identifier.isbn978-1-5386-6651-7
dc.identifier.issn1062-922X
dc.identifier.urihttps://depositonce.tu-berlin.de/handle/11303/12351
dc.identifier.urihttp://dx.doi.org/10.14279/depositonce-11191
dc.language.isoenen
dc.relation.ispartof10.14279/depositonce-10656
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subject.ddc153 Kognitive Prozesse, Intelligenzde
dc.subject.ddc004 Datenverarbeitung; Informatikde
dc.subject.otherscalpen
dc.subject.otherbrain modelingen
dc.subject.otherelectroencephalographyen
dc.subject.otherfeature extractionen
dc.subject.othertransformsen
dc.subject.othervisualizationen
dc.titleTowards classifier visualisation in 3D source spaceen
dc.typeConference Objecten
dc.type.versionacceptedVersionen
dcterms.bibliographicCitation.articlenumber18410764en
dcterms.bibliographicCitation.doi10.1109/SMC.2018.00022en
dcterms.bibliographicCitation.originalpublishernameIEEEen
dcterms.bibliographicCitation.originalpublisherplaceNew York, NYen
dcterms.bibliographicCitation.proceedingstitle2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC)en
dcterms.bibliographicCitation.volume2018en
tub.accessrights.dnbdomain*
tub.affiliationFak. 5 Verkehrs- und Maschinensysteme::Inst. Psychologie und Arbeitswissenschaft::FG Biopsychologie und Neuroergonomiede
tub.affiliation.facultyFak. 5 Verkehrs- und Maschinensystemede
tub.affiliation.groupFG Biopsychologie und Neuroergonomiede
tub.affiliation.instituteInst. Psychologie und Arbeitswissenschaftde
tub.publisher.universityorinstitutionTechnische Universität Berlinen

Files

Original bundle
Now showing 1 - 1 of 1
Loading…
Thumbnail Image
Name:
Krol_etal_Towards_2019.pdf
Size:
1.92 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.9 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections