Dynamic statistical classification

dc.creatorPulido-Cejudo,Javier
dc.creatorCuevas-Covarrubias,Carlos
dc.date2017-06-01
dc.date.accessioned2023-09-25T14:12:10Z
dc.date.available2023-09-25T14:12:10Z
dc.identifierhttp://www.scielo.sa.cr/scielo.php?script=sci_arttext&pid=S1409-24332017000100115
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/8814962
dc.descriptionAbstractWe consider the statistical supervised classification problem from a dynamical systems approach. We assume that two classes exist and that, for each one, a multivariate normal distribution determines the probability to be in a certain region in the n dimensional real vector space. These density functions are the potentials of corresponding gradient vector fields for each class; we construct a “classifying vector field” as a suitable weighted mean of them. From data known in the literature, we estimate the population parameters, and the classes are successfully distinguished; we compute and present confusion matrices. A one and two-dimensional analysis is given.
dc.formattext/html
dc.languageen
dc.publisherCentro de Investigaciones en Matemática Pura y Aplicada (CIMPA) y Escuela de Matemática, San José, Costa Rica.
dc.relation10.15517/rmta.v24i1.27774
dc.rightsinfo:eu-repo/semantics/openAccess
dc.sourceRevista de Matemática Teoría y Aplicaciones v.24 n.1 2017
dc.subjectsupervised statistical classification
dc.subjectmultivariate normal distribution
dc.subjectvector fields
dc.subjectattractors
dc.subjectbifurcation
dc.subjectdynamical systems
dc.titleDynamic statistical classification
dc.typeinfo:eu-repo/semantics/article


Este ítem pertenece a la siguiente institución