Show simple item record

Support Vector Machines for Nonlinear Kernel ARMA System Identification

dc.contributor.authorMartínez Ramón, Manel
dc.contributor.authorRojo-Álvarez, José Luis
dc.contributor.authorCamps Valls, Gustavo
dc.contributor.authorMuñoz Marí, Jordi
dc.contributor.authorNavia Vázquez, Ángel
dc.contributor.authorSoria Olivas, Emilio
dc.contributor.authorFigueiras Vidal, Aníbal R
dc.date.accessioned2009-02-04T19:08:30Z
dc.date.available2009-02-04T19:08:30Z
dc.date.issued2006-11-01
dc.identifier.issn1045-9227
dc.identifier.urihttp://hdl.handle.net/10115/1913
dc.description.abstractNonlinear system identification based on support vector machines (SVM) has been usually addressed by means of the standard SVM regression (SVR), which can be seen as an implicit nonlinear autoregressive and moving average (ARMA) model in some reproducing kernel Hilbert space (RKHS). The proposal of this letter is twofold. First, the explicit consideration of an ARMA model in an RKHS (SVM-ARMA 2k) is proposed. We show that stating the ARMA equations in an RKHS leads to solving the regularized normal equations in that RKHS, in terms of the autocorrelation and cross correlation of the (nonlinearly) transformed input and output discrete time processes. Second, a general class of SVM-based system identification nonlinear models is presented, based on the use of composite Mercer¿s kernels. This general class can improve model flexibility by emphasizing the input¿output cross information (SVM-ARMA 4k), which leads to straightforward and natural combinations of implicit and explicit ARMA models (SVR-ARMA 2k and SVR-ARMA 4k). Capabilities of these different SVM-based system identification schemes are illustrated with two benchmark problems.es
dc.language.isoenes
dc.relation.ispartofseriesIEEE Transactions on Neural Networkses
dc.relation.ispartofseries17(6)es
dc.rightsAtribución-NoComercial-SinDerivadas 3.0 España*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/*
dc.subjectTelecomunicacioneses
dc.titleSupport Vector Machines for Nonlinear Kernel ARMA System Identificationes
dc.typeinfo:eu-repo/semantics/articlees
dc.rights.accessRightsinfo:eu-repo/semantics/openAccesses
dc.subject.unesco3325 Tecnología de las Telecomunicacioneses
dc.description.departamentoTeoría de la Señal y Comunicaciones


Files in this item

This item appears in the following Collection(s)

Show simple item record

Atribución-NoComercial-SinDerivadas 3.0 EspañaExcept where otherwise noted, this item's license is described as Atribución-NoComercial-SinDerivadas 3.0 España