Show simple item record

dc.contributor.authorHernández-Pereira, Elena
dc.contributor.authorBolón-Canedo, Verónica
dc.contributor.authorSánchez-Maroño, Noelia
dc.contributor.authorÁlvarez-Estévez, Diego
dc.contributor.authorMoret-Bonillo, Vicente
dc.contributor.authorAlonso-Betanzos, Amparo
dc.date.accessioned2017-02-10T17:10:45Z
dc.date.issued2016-01-20
dc.identifier.citationElena Hernández-Pereira, Veronica Bolón-Canedo, Noelia Sánchez-Maroño, Diego Álvarez-Estévez, Vicente Moret-Bonillo, Amparo Alonso-Betanzos, Information Sciences, Information Sciences 328 (2016), pp. 1–14es_ES
dc.identifier.issn0020-0255
dc.identifier.issn1872-6291
dc.identifier.urihttp://hdl.handle.net/2183/18099
dc.descriptionThe final publication is available at ScienceDirect via http://dx.doi.org/10.1016/j.ins.2015.08.022es_ES
dc.description.abstract[Abstract] The main objective of this work is to obtain a method that achieves the best accuracy results with a low false positive rate in the classification of K-complexes, a kind of transient waveform found in the Electroencephalogram. With this in mind, the capabilities of several machine learning techniques were tried. The inputs for the models were a set of features based on amplitude and duration measurements obtained from waveforms to be classified. Among all the classifiers tested, the Support Vector Machine obtained the best results with an accuracy of 88.69%. Finally, to enhance the generalization capabilities of the classifiers, while at the same time discarding the existing irrelevant features, feature selection methods were employed. After this process, the classification performance was significantly improved. The best result was obtained applying a correlation-based filter, achieving a 91.40% of accuracy using only 36% of the total input features.es_ES
dc.description.sponsorshipXunta de Galicia; 09SIN003CTes_ES
dc.description.sponsorshipMinisterio de Economía y Competitividad; TIN2013-40686Pes_ES
dc.description.sponsorshipMinisterio de Economía y Competitividad; TIN2012-37954
dc.description.sponsorshipXunta de Galicia; GRC2014/35
dc.language.isoenges_ES
dc.relation.urihttp://www.sciencedirect.com/science/article/pii/S0020025515006088es_ES
dc.rightsAtribución-NoComercial-SinDerivadas 3.0 Españaes_ES
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/*
dc.subjectFeature selection Machine learninges_ES
dc.subjectK-complex classificationes_ES
dc.titleA comparison of performance of K-complex classification methods using feature selectiones_ES
dc.typeinfo:eu-repo/semantics/articlees_ES
dc.rights.accessinfo:eu-repo/semantics/embargoedAccesses_ES
dc.date.embargoEndDate2018-01-20es_ES
dc.date.embargoLift2018-01-20
UDC.journalTitleInformation Scienceses_ES
UDC.volume328es_ES
UDC.startPage1es_ES
UDC.endPage14es_ES
dc.identifier.doi10.1016/j.ins.2015.08.022


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record