Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/17184
DC FieldValueLanguage
dc.contributorDepartment of Electronic and Information Engineering-
dc.creatorLeung, FHF-
dc.creatorLing, SH-
dc.creatorLam, HK-
dc.date.accessioned2015-06-23T09:15:53Z-
dc.date.available2015-06-23T09:15:53Z-
dc.identifier.issn1469-0268-
dc.identifier.urihttp://hdl.handle.net/10397/17184-
dc.language.isoenen_US
dc.publisherImperial College Pressen_US
dc.subjectGenetic algorithmen_US
dc.subjectNeural networken_US
dc.subjectPattern recognitionen_US
dc.subjectSunspot forecastingen_US
dc.titleAn improved genetic-algorithm-based neural-tuned neural networken_US
dc.typeJournal/Magazine Articleen_US
dc.identifier.spage469-
dc.identifier.epage492-
dc.identifier.volume7-
dc.identifier.issue4-
dc.identifier.doi10.1142/S1469026808002375-
dcterms.abstractThis paper presents a neural-tuned neural network (NTNN), which is trained by an improved genetic algorithm (GA). The NTNN consists of a common neural network and a modified neural network (MNN). In the MNN, a neuron model with two activation functions is introduced. An improved GA is proposed to train the parameters of the proposed network. A set of improved genetic operations are presented, which show superior performance over the traditional GA. The proposed network structure can increase the search space of the network and offer better performance than the traditional feed-forward neural network. Two application examples are given to illustrate the merits of the proposed network and the improved GA.-
dcterms.bibliographicCitationInternational journal of computational intelligence and applications, 2008, v. 7, no. 4, p. 469-492-
dcterms.isPartOfInternational journal of computational intelligence and applications-
dcterms.issued2008-
dc.identifier.scopus2-s2.0-64349115741-
dc.identifier.eissn1757-5885-
dc.identifier.rosgroupidr44029-
dc.description.ros2008-2009 > Academic research: refereed > Publication in refereed journal-
Appears in Collections:Journal/Magazine Article
Access
View full-text via PolyU eLinks SFX Query
Show simple item record

SCOPUSTM   
Citations

2
Last Week
0
Last month
0
Citations as of Sep 4, 2020

Page view(s)

142
Last Week
2
Last month
Citations as of Oct 21, 2020

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.