Publication:
Improving classification for brain computer interfaces using transitions and a moving window

Simple item page
dc.affiliation.dptoUC3M. Departamento de Informáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Computación Evolutiva y Redes Neuronales (EVANNAI)es
dc.contributor.authorAler, Ricardo
dc.contributor.authorGalván, Inés M.
dc.contributor.authorValls, José M.
dc.date.accessioned2010-12-16T09:55:10Z
dc.date.available2010-12-16T09:55:10Z
dc.date.issued2009-01-14
dc.descriptionProceeding of: Biosignals 2009. International Conference on Bio-inspired Systems and Signal Processing, BIOSTEC 2009. Porto (Portugal), 14-17 January 2009
dc.description.abstractThe context of this paper is the brain-computer interface (BCI), and in particular the classification of signals with machine learning methods. In this paper we intend to improve classification accuracy by taking advantage of a feature of BCIs: instances run in sequences belonging to the same class. In that case, the classiffication problem can be reformulated into two subproblems: detecting class transitions and determining the class for sequences of instances between transitions. We detect a transition when the Euclidean distance between the power spectra at two different times is larger than a threshold. To tackle the second problem, instances are classified by taking into account, not just the prediction for that instance, but a moving window of predictions for previous instances. Experimental results show that our transition detection method improves results for datasets of two out of three subjects of the BCI III competition. If the moving window is used, classification accuracy is further improved, depending on the window size.
dc.description.statusPublicado
dc.format.mimetypeapplication/octet-stream
dc.format.mimetypeapplication/octet-stream
dc.format.mimetypeapplication/octet-stream
dc.format.mimetypetext/plain
dc.format.mimetypeapplication/pdf
dc.identifier.bibliographicCitationBiomedical Engineering Systems and Technologies International Joint Conference, BIOSTEC 2009. Springer, 2009, pp. 200-210
dc.identifier.doi10.1007/978-3-642-11721-3_15
dc.identifier.isbn978-3-642-11720-6
dc.identifier.issn1865-0929
dc.identifier.publicationfirstpage200
dc.identifier.publicationlastpage210
dc.identifier.publicationtitleBiomedical Engineering Systems and Technologies International Joint Conference, BIOSTEC 2009
dc.identifier.urihttps://hdl.handle.net/10016/6760
dc.language.isoeng
dc.relation.eventdate14-17 January 2009
dc.relation.eventplacePorto (Portugal)
dc.relation.eventtitleBiosignals 2009. International Conference on Bio-inspired Systems and Signal Processing, BIOSTEC 2009
dc.relation.ispartofseriesCommunications in computer and information science, vol. 52
dc.relation.publisherversionhttp://dx.doi.org/10.1007/978-3-642-11721-3_15
dc.rights© Springer
dc.rights.accessRightsopen access
dc.subject.ecienciaInformática
dc.subject.otherBrain computer interface
dc.titleImproving classification for brain computer interfaces using transitions and a moving window
dc.typeconference paper*
dc.type.reviewPeerReviewed
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
improving_Aler_BIOSTEC-2009.pdf
Size:
169.58 KB
Format:
Adobe Portable Document Format
Download
Collections
DI - GCERN - Comunicaciones en Congresos y otros eventos
DI - GCERN - Capítulos de Monografías