Improving Parkinson's disease identification through evolutionary-based feature selection

dc.contributorUniversidade Estadual Paulista (UNESP)
dc.creatorSpadoto, André A.
dc.creatorGuido, Rodrigo C.
dc.creatorCarnevali, Felipe L.
dc.creatorPagnin, Andre F.
dc.creatorFalcão, Alexandre X.
dc.creatorPapa, João Paulo
dc.date2014-05-27T11:26:20Z
dc.date2016-10-25T18:36:22Z
dc.date2014-05-27T11:26:20Z
dc.date2016-10-25T18:36:22Z
dc.date2011-12-26
dc.date.accessioned2017-04-06T01:56:29Z
dc.date.available2017-04-06T01:56:29Z
dc.identifierProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, p. 7857-7860.
dc.identifier1557-170X
dc.identifierhttp://hdl.handle.net/11449/73086
dc.identifierhttp://acervodigital.unesp.br/handle/11449/73086
dc.identifier10.1109/IEMBS.2011.6091936
dc.identifier2-s2.0-84055219309
dc.identifierhttp://dx.doi.org/10.1109/IEMBS.2011.6091936
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/893911
dc.descriptionParkinson's disease (PD) automatic identification has been actively pursued over several works in the literature. In this paper, we deal with this problem by applying evolutionary-based techniques in order to find the subset of features that maximize the accuracy of the Optimum-Path Forest (OPF) classifier. The reason for the choice of this classifier relies on its fast training phase, given that each possible solution to be optimized is guided by the OPF accuracy. We also show results that improved other ones recently obtained in the context of PD automatic identification. © 2011 IEEE.
dc.languageeng
dc.relationProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectAutomatic identification
dc.subjectParkinson's disease
dc.subjectPossible solutions
dc.subjectTraining phase
dc.subjectAutomation
dc.subjectNeurodegenerative diseases
dc.subjectFeature extraction
dc.titleImproving Parkinson's disease identification through evolutionary-based feature selection
dc.typeOtro


Este ítem pertenece a la siguiente institución