Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/58955
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Watts, M. | - |
dc.contributor.author | Worner, S. | - |
dc.date.issued | 2006 | - |
dc.identifier.citation | International Journal of Information Technology, 2006; 12(6):35-42 | - |
dc.identifier.issn | 1305-239X | - |
dc.identifier.issn | 0218-7957 | - |
dc.identifier.uri | http://hdl.handle.net/2440/58955 | - |
dc.description.abstract | A 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. | - |
dc.description.statementofresponsibility | Watts, M.J. and Worner, S.P | - |
dc.language.iso | en | - |
dc.publisher | International Academy of Sciences | - |
dc.rights | (C) Singapore computer society 2006 | - |
dc.subject | Self-Organising Maps | - |
dc.subject | Evolving Connectionist Systems | - |
dc.subject | pest invasion prediction | - |
dc.title | Comparison of a self organising map and simple evolving connectionist system for predicting insect pest establishment | - |
dc.type | Journal article | - |
pubs.publication-status | Published | - |
Appears in Collections: | Aurora harvest 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.