File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Model Selection for RBF Network via Generalized Degree of Freedom

TitleModel Selection for RBF Network via Generalized Degree of Freedom
Authors
Issue Date2013
PublisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/neucom
Citation
Neurocomputing, 2013, v. 99, p. 163-171 How to Cite?
AbstractRadial basis function (RBF) networks are considered in this study to simulate and forecast a chaotic time series. In order to evaluate the performance of the RBF networks, a new method is developed to calculate the generalized degree of freedom (GDF), which is used to obtain an unbiased estimation of variance of the fitted model error for the network. Numerical results show that the proposed estimation of GDF is more stable and faster than that obtained by the Monte Carlo method. A model selection method using GDF for a chaotic time series is then introduced and applied to four chaotic time series. The numerical results show that the network selected by the proposed method gives better prediction ability. © 2012 Elsevier B.V.
Persistent Identifierhttp://hdl.handle.net/10722/191285
ISSN
2015 Impact Factor: 2.392
2015 SCImago Journal Rankings: 1.202
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorXu, P-
dc.contributor.authorJayawardena, AW-
dc.contributor.authorLi, WK-
dc.date.accessioned2013-10-15T06:53:04Z-
dc.date.available2013-10-15T06:53:04Z-
dc.date.issued2013-
dc.identifier.citationNeurocomputing, 2013, v. 99, p. 163-171-
dc.identifier.issn0925-2312-
dc.identifier.urihttp://hdl.handle.net/10722/191285-
dc.description.abstractRadial basis function (RBF) networks are considered in this study to simulate and forecast a chaotic time series. In order to evaluate the performance of the RBF networks, a new method is developed to calculate the generalized degree of freedom (GDF), which is used to obtain an unbiased estimation of variance of the fitted model error for the network. Numerical results show that the proposed estimation of GDF is more stable and faster than that obtained by the Monte Carlo method. A model selection method using GDF for a chaotic time series is then introduced and applied to four chaotic time series. The numerical results show that the network selected by the proposed method gives better prediction ability. © 2012 Elsevier B.V.-
dc.languageeng-
dc.publisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/neucom-
dc.relation.ispartofNeurocomputing-
dc.titleModel Selection for RBF Network via Generalized Degree of Freedom-
dc.typeArticle-
dc.identifier.emailJayawardena, AW: hrecjaw@hkucc.hku.hk-
dc.identifier.emailLi, WK: hrntlwk@hkucc.hku.hk-
dc.identifier.authorityLi, WK=rp00741-
dc.identifier.doi10.1016/j.neucom.2012.06.005-
dc.identifier.scopuseid=2-s2.0-84867879601-
dc.identifier.hkuros225261-
dc.identifier.volume99-
dc.identifier.spage163-
dc.identifier.epage171-
dc.identifier.isiWOS:000311129300016-
dc.publisher.placeNetherlands-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats