Aprendizado de máquina simbólico e técnicas fractais para caracterizar rejeição em biópsia miocárdica

dc.contributorUniversidade Estadual Paulista (UNESP)
dc.creatorCarvalho, V. O.
dc.creatorNeves, L. A.
dc.creatorDe Godoy, M. F.
dc.creatorMoreira, R. D.
dc.creatorMoriel, A. R.
dc.creatorMurta, L. O.
dc.date2014-05-27T11:28:42Z
dc.date2016-10-25T18:45:50Z
dc.date2014-05-27T11:28:42Z
dc.date2016-10-25T18:45:50Z
dc.date2013-03-26
dc.date.accessioned2017-04-06T02:17:21Z
dc.date.available2017-04-06T02:17:21Z
dc.identifier5th Latin American Congress on Biomedical Engineering (claib 2011): Sustainable Technologies For the Health of All, Pts 1 and 2. New York: Springer, v. 33, n. 1-2, p. 272-275, 2013.
dc.identifier1680-0737
dc.identifierhttp://hdl.handle.net/11449/74875
dc.identifierhttp://acervodigital.unesp.br/handle/11449/74875
dc.identifier10.1007/978-3-642-21198-0_70
dc.identifier2-s2.0-84875250024
dc.identifierhttp://dx.doi.org/10.1007/978-3-642-21198-0_70
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/895634
dc.descriptionThis work combines symbolic machine learning and multiscale fractal techniques to generate models that characterize cellular rejection in myocardial biopsies and that can base a diagnosis support system. The models express the knowledge by the features threshold, fractal dimension, lacunarity, number of clusters, spatial percolation and percolation probability, all obtained with myocardial biopsies processing. Models were evaluated and the most significant was the one generated by the C4.5 algorithm for the features spatial percolation and number of clusters. The result is relevant and contributes to the specialized literature since it determines a standard diagnosis protocol. © 2013 Springer.
dc.languagepor
dc.relationIFMBE Proceedings
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectmultiscale fractal techniques
dc.subjectmyocardial biopsies images
dc.subjectsymbolic machine learning
dc.subjectC4.5 algorithm
dc.subjectDiagnosis support systems
dc.subjectLacunarity
dc.subjectMultiscale fractals
dc.subjectNumber of clusters
dc.subjectPercolation probability
dc.subjectSymbolic machine learning
dc.subjectBiomedical engineering
dc.subjectFractal dimension
dc.subjectLearning systems
dc.subjectSolvents
dc.subjectBiopsy
dc.titleAprendizado de máquina simbólico e técnicas fractais para caracterizar rejeição em biópsia miocárdica
dc.typeOtro


Este ítem pertenece a la siguiente institución