Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/58955
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWatts, M.en
dc.contributor.authorWorner, S.en
dc.date.issued2006en
dc.identifier.citationInternational Journal of Information Technology, 2006; 12(6):35-42en
dc.identifier.issn1305-239Xen
dc.identifier.issn0218-7957en
dc.identifier.urihttp://hdl.handle.net/2440/58955-
dc.description.abstractA comparison of two artificial neural network methods for predicting the risk of insect pest species establishment in regions where they are not normally found is presented. The ANN methods include a well-known unsupervised learning algorithm and a relatively new supervised constructive method. A New Zealand pest species assemblage as an example was used to compare model predictions. Both methods gave similar results for already established and non-established species.en
dc.description.statementofresponsibilityWatts, M.J. and Worner, S.Pen
dc.language.isoenen
dc.publisherInternational Academy of Sciencesen
dc.rights(C) Singapore computer society 2006en
dc.subjectSelf-Organising Maps; Evolving Connectionist Systems; pest invasion predictionen
dc.titleComparison of a self organising map and simple evolving connectionist system for predicting insect pest establishmenten
dc.typeJournal articleen
dc.identifier.rmid0020103739en
dc.identifier.pubid31906-
pubs.library.collectionEarth and Environmental Sciences publicationsen
pubs.verification-statusVerifieden
pubs.publication-statusPublisheden
Appears in Collections:Earth and Environmental Sciences publications
Environment Institute publications

Files in This Item:
There are no files associated with this item.


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