File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Evolutionary product unit based neural networks for hydrological time series analysis

TitleEvolutionary product unit based neural networks for hydrological time series analysis
Authors
KeywordsEvolutionary algorithms
Neural networks
Prediction
Time series
Issue Date2011
PublisherI W A Publishing. The Journal's web site is located at http://www.iwapublishing.com/template.cfm?name=iwapjhi
Citation
Journal Of Hydroinformatics, 2011, v. 13 n. 4, p. 825-841 How to Cite?
AbstractArtificial Neural Networks (ANNs) are now widely used in many areas of science, medicine, finance and engineering. Analysis and prediction of time series of hydrological/and meteorological data is one such application. Problems that still exist in the application of ANN's are the lack of transparency and the expertise needed for training. An evolutionary algorithm-based method to train a type of neural networks called Product Units Based Neural Networks (PUNN) has been proposed in a 2006 study. This study investigates the applicability of this type of neural networks to hydrological time series prediction. The technique, with a few small changes to improve the performance, is applied to some benchmark time series as well as to a real hydrological time series for prediction. The results show that evolutionary PUNN produce more transparent models compared to widely used multilayer perceptron (MLP) neural network models. It is also seen that training of PUNN models requires less expertise compared to MLPs. © WA Publishing 2011.
Persistent Identifierhttp://hdl.handle.net/10722/135493
ISSN
2023 Impact Factor: 2.2
2023 SCImago Journal Rankings: 0.573
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorKarunasingha, DSKen_HK
dc.contributor.authorJayawardena, AWen_HK
dc.contributor.authorLi, WKen_HK
dc.date.accessioned2011-07-27T01:36:04Z-
dc.date.available2011-07-27T01:36:04Z-
dc.date.issued2011en_HK
dc.identifier.citationJournal Of Hydroinformatics, 2011, v. 13 n. 4, p. 825-841en_HK
dc.identifier.issn1464-7141en_HK
dc.identifier.urihttp://hdl.handle.net/10722/135493-
dc.description.abstractArtificial Neural Networks (ANNs) are now widely used in many areas of science, medicine, finance and engineering. Analysis and prediction of time series of hydrological/and meteorological data is one such application. Problems that still exist in the application of ANN's are the lack of transparency and the expertise needed for training. An evolutionary algorithm-based method to train a type of neural networks called Product Units Based Neural Networks (PUNN) has been proposed in a 2006 study. This study investigates the applicability of this type of neural networks to hydrological time series prediction. The technique, with a few small changes to improve the performance, is applied to some benchmark time series as well as to a real hydrological time series for prediction. The results show that evolutionary PUNN produce more transparent models compared to widely used multilayer perceptron (MLP) neural network models. It is also seen that training of PUNN models requires less expertise compared to MLPs. © WA Publishing 2011.en_HK
dc.languageengen_US
dc.publisherI W A Publishing. The Journal's web site is located at http://www.iwapublishing.com/template.cfm?name=iwapjhien_HK
dc.relation.ispartofJournal of Hydroinformaticsen_HK
dc.rightsJournal of Hydroinformatics. Copyright © IWA Publishing.-
dc.subjectEvolutionary algorithmsen_HK
dc.subjectNeural networksen_HK
dc.subjectPredictionen_HK
dc.subjectTime seriesen_HK
dc.titleEvolutionary product unit based neural networks for hydrological time series analysisen_HK
dc.typeArticleen_HK
dc.identifier.emailLi, WK: hrntlwk@hku.hken_HK
dc.identifier.authorityLi, WK=rp00741en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.2166/hydro.2010.099en_HK
dc.identifier.scopuseid_2-s2.0-80055022705en_HK
dc.identifier.hkuros186737en_US
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-80055022705&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume13en_HK
dc.identifier.issue4en_HK
dc.identifier.spage825en_HK
dc.identifier.epage841en_HK
dc.identifier.isiWOS:000296242100018-
dc.publisher.placeUnited Kingdomen_HK
dc.identifier.scopusauthoridKarunasingha, DSK=53880133200en_HK
dc.identifier.scopusauthoridJayawardena, AW=7005049253en_HK
dc.identifier.scopusauthoridLi, WK=14015971200en_HK
dc.identifier.issnl1464-7141-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats