A path- and label-cost propagation approach to speedup the training of the optimum-path forest classifier

dc.creatorIwashita, AS
dc.creatorPapa, JP
dc.creatorSouza, AN
dc.creatorFalcao, AX
dc.creatorLotufo, RA
dc.creatorOliveira, VM
dc.creatorde Albuquerque, VHC
dc.creatorTavares, JMRS
dc.date2014
dc.dateAPR 15
dc.date2014-08-01T18:17:18Z
dc.date2015-11-26T17:01:30Z
dc.date2014-08-01T18:17:18Z
dc.date2015-11-26T17:01:30Z
dc.date.accessioned2018-03-28T23:49:20Z
dc.date.available2018-03-28T23:49:20Z
dc.identifierPattern Recognition Letters. Elsevier Science Bv, v. 40, n. 121, n. 127, 2014.
dc.identifier0167-8655
dc.identifier1872-7344
dc.identifierWOS:000333105600016
dc.identifier10.1016/j.patrec.2013.12.018
dc.identifierhttp://www.repositorio.unicamp.br/jspui/handle/REPOSIP/76617
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/76617
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1278739
dc.descriptionIn general, pattern recognition techniques require a high computational burden for learning the discriminating functions that are responsible to separate samples from distinct classes. As such, there are several studies that make effort to employ machine learning algorithms in the context of 'big data' classification problems. The research on this area ranges from Graphics Processing Units-based implementations to mathematical optimizations, being the main drawback of the former approaches to be dependent on the graphic video card. Here, we propose an architecture-independent optimization approach for the optimum-path forest (OPF) classifier, that is designed using a theoretical formulation that relates the minimum spanning tree with the minimum spanning forest generated by the OPF over the training dataset. The experiments have shown that the approach proposed can be faster than the traditional one in five public datasets, being also as accurate as the original OPF. (C) 2014 Elsevier B. V. All rights reserved.
dc.description40
dc.description121
dc.description127
dc.descriptionFundacao para a Ciencia e a Tecnologia (FCT) in Portugal [PTDC/BBB-BMD/3088/2012]
dc.descriptionFundacao para a Ciencia e a Tecnologia (FCT) in Portugal [PTDC/BBB-BMD/3088/2012]
dc.languageen
dc.publisherElsevier Science Bv
dc.publisherAmsterdam
dc.publisherHolanda
dc.relationPattern Recognition Letters
dc.relationPattern Recognit. Lett.
dc.rightsfechado
dc.rightshttp://www.elsevier.com/about/open-access/open-access-policies/article-posting-policy
dc.sourceWeb of Science
dc.subjectMachine learning
dc.subjectPattern recognition
dc.subjectOptimum-path forest
dc.titleA path- and label-cost propagation approach to speedup the training of the optimum-path forest classifier
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución