Minimizing inter-subject variability in fNIRS-based brain–computer interfaces via multiple-kernel support vector learning

Simple item page
dc.contributor.authorAbibullaev, Berdakh
dc.contributor.authorAn, Jinung
dc.contributor.authorJin, Sang-Hyeon
dc.contributor.authorLee, Seung Hyun
dc.contributor.authorMoon, Jeon Il
dc.creatorBerdakh, Abibullaev
dc.date.accessioned2017-12-21T06:22:35Z
dc.date.available2017-12-21T06:22:35Z
dc.date.issued2013-12-01
dc.description.abstractAbstract Brain signal variation across different subjects and sessions significantly impairs the accuracy of most brain–computer interface (BCI) systems. Herein, we present a classification algorithm that minimizes such variation, using linear programming support-vector machines (LP-SVM) and their extension to multiple kernel learning methods. The minimization is based on the decision boundaries formed in classifiers’ feature spaces and their relation to BCI variation. Specifically, we estimate subject/session-invariant features in the reproducing kernel Hilbert spaces (RKHS) induced with Gaussian kernels. The idea is to construct multiple subject/session-dependent RKHS and to perform classification with LP-SVMs. To evaluate the performance of the algorithm, we applied it to oxy-hemoglobin data sets acquired from eight sessions and seven subjects as they performed two different mental tasks. Results show that our classifiers maintain good performance when applied to random patterns across varying sessions/subjects.en_US
dc.identifierDOI:10.1016/j.medengphy.2013.08.009
dc.identifier.citationBerdakh Abibullaev, Jinung An, Sang-Hyeon Jin, Seung Hyun Lee, Jeon Il Moon, Minimizing inter-subject variability in fNIRS-based brain–computer interfaces via multiple-kernel support vector learning, In Medical Engineering & Physics, Volume 35, Issue 12, 2013, Pages 1811-1818en_US
dc.identifier.issn13504533
dc.identifier.urihttps://www.sciencedirect.com/science/article/pii/S1350453313001835
dc.identifier.urihttp://nur.nu.edu.kz/handle/123456789/3008
dc.language.isoenen_US
dc.publisherMedical Engineering & Physicsen_US
dc.relation.ispartofMedical Engineering & Physics
dc.rights.licenseCopyright © 2013 IPEM. Published by Elsevier Ltd. All rights reserved.
dc.subjectBrain–computer interfacesen_US
dc.subjectFunctional near-infrared spectroscopyen_US
dc.subjectInter-subject variabilityen_US
dc.subjectSupport vector machinesen_US
dc.subjectRKHSen_US
dc.subjectMultiple kernel learningen_US
dc.titleMinimizing inter-subject variability in fNIRS-based brain–computer interfaces via multiple-kernel support vector learningen_US
dc.typeArticleen_US
elsevier.aggregationtypeJournal
elsevier.coverdate2013-12-01
elsevier.coverdisplaydateDecember 2013
elsevier.endingpage1818
elsevier.identifier.doi10.1016/j.medengphy.2013.08.009
elsevier.identifier.eid1-s2.0-S1350453313001835
elsevier.identifier.piiS1350-4533(13)00183-5
elsevier.identifier.pubmedid24054981
elsevier.identifier.scopusid84889593590
elsevier.issue.identifier12
elsevier.openaccess0
elsevier.openaccessarticlefalse
elsevier.openarchivearticlefalse
elsevier.startingpage1811
elsevier.teaserBrain signal variation across different subjects and sessions significantly impairs the accuracy of most brain–computer interface (BCI) systems. Herein, we present a classification algorithm that minimizes...
elsevier.volume35
workflow.import.sourcescience

Files

Collections

Articles