File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Modelling of river discharges and rainfall using radial basis function networks based on support vector regression

TitleModelling of river discharges and rainfall using radial basis function networks based on support vector regression
Authors
Issue Date2003
PublisherTaylor & Francis Ltd. The Journal's web site is located at http://www.tandf.co.uk/journals/titles/00207721.asp
Citation
International Journal Of Systems Science, 2003, v. 34 n. 14-15, p. 763-773 How to Cite?
AbstractAssociative memory networks (AMNs) based on radial basis functions (RBFs) are often used to model complex and nonlinear systems, as they can approximate nonlinear systems with arbitrary accuracy and can be trained from data. However, good generalization results can only be obtained if the structure of the RBF network is suitably chosen. An approach to select the structure of the RBF networks based on the support vectors (SVs) of the support vector machine (SVM) has been proposed. The main advantage of this approach is that the structure of the network can be obtained objectively, as the SVs of the SVM are obtained from a constrained optimization for a given error bound. For convenience, this class of AMNs is referred to as support vector radial basis function networks (SVRBFNs). In this paper, the modelling of the relationship between rainfall and river discharges of the Fuji river using the SVRBFN is presented. As there are large outliers in the modelling errors arising from the data collection process, they are removed first before retraining the SVRBFN using the adjusted data, in order to obtain a better approximation of the relationship between rainfall and river discharges. The generalization ability of the SVRBFN is verified using the test data that are the most recent not used in the training of the network. The prediction of river discharges for given rainfalls can be computed from the SVRBFN, which can provide early warning of severe river discharges when there is heavy and prolonged rainfall.
Persistent Identifierhttp://hdl.handle.net/10722/75656
ISSN
2015 Impact Factor: 1.947
2015 SCImago Journal Rankings: 1.083
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorChoy, KYen_HK
dc.contributor.authorChan, CWen_HK
dc.date.accessioned2010-09-06T07:13:17Z-
dc.date.available2010-09-06T07:13:17Z-
dc.date.issued2003en_HK
dc.identifier.citationInternational Journal Of Systems Science, 2003, v. 34 n. 14-15, p. 763-773en_HK
dc.identifier.issn0020-7721en_HK
dc.identifier.urihttp://hdl.handle.net/10722/75656-
dc.description.abstractAssociative memory networks (AMNs) based on radial basis functions (RBFs) are often used to model complex and nonlinear systems, as they can approximate nonlinear systems with arbitrary accuracy and can be trained from data. However, good generalization results can only be obtained if the structure of the RBF network is suitably chosen. An approach to select the structure of the RBF networks based on the support vectors (SVs) of the support vector machine (SVM) has been proposed. The main advantage of this approach is that the structure of the network can be obtained objectively, as the SVs of the SVM are obtained from a constrained optimization for a given error bound. For convenience, this class of AMNs is referred to as support vector radial basis function networks (SVRBFNs). In this paper, the modelling of the relationship between rainfall and river discharges of the Fuji river using the SVRBFN is presented. As there are large outliers in the modelling errors arising from the data collection process, they are removed first before retraining the SVRBFN using the adjusted data, in order to obtain a better approximation of the relationship between rainfall and river discharges. The generalization ability of the SVRBFN is verified using the test data that are the most recent not used in the training of the network. The prediction of river discharges for given rainfalls can be computed from the SVRBFN, which can provide early warning of severe river discharges when there is heavy and prolonged rainfall.en_HK
dc.languageengen_HK
dc.publisherTaylor & Francis Ltd. The Journal's web site is located at http://www.tandf.co.uk/journals/titles/00207721.aspen_HK
dc.relation.ispartofInternational Journal of Systems Scienceen_HK
dc.titleModelling of river discharges and rainfall using radial basis function networks based on support vector regressionen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0020-7721&volume=34&issue=14-15&spage=763&epage=773&date=2003&atitle=Modelling+of+river+discharges+and+rainfall+using+radial+basis+function+networks+based+on+support+vector+regressionen_HK
dc.identifier.emailChan, CW: mechan@hkucc.hku.hken_HK
dc.identifier.authorityChan, CW=rp00088en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1080/00207720310001640241en_HK
dc.identifier.scopuseid_2-s2.0-1642578192en_HK
dc.identifier.hkuros89129en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-1642578192&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume34en_HK
dc.identifier.issue14-15en_HK
dc.identifier.spage763en_HK
dc.identifier.epage773en_HK
dc.identifier.isiWOS:000188453700004-
dc.publisher.placeUnited Kingdomen_HK
dc.identifier.scopusauthoridChoy, KY=7005477038en_HK
dc.identifier.scopusauthoridChan, CW=7404814060en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats