Improving neural network performance on the classification of complex geographic datasets

Mark Gahegan, Gordon German and Geoff West
Additional contact information
Mark Gahegan: Department of Geographic Information Science, Curtin University of Technology, P.O. Box U1987, Perth, Western Australia 6845, Australia (e-mail: mark, gordon, geoff@cs.curtin.edu.au)
Gordon German: Department of Geographic Information Science, Curtin University of Technology, P.O. Box U1987, Perth, Western Australia 6845, Australia (e-mail: mark, gordon, geoff@cs.curtin.edu.au)
Geoff West: Department of Geographic Information Science, Curtin University of Technology, P.O. Box U1987, Perth, Western Australia 6845, Australia (e-mail: mark, gordon, geoff@cs.curtin.edu.au)

Journal of Geographical Systems, 1999, vol. 1, issue 1, 3-22

Abstract: Abstract. Neural Networks are now established computational tools used for search minimisation and data classification. They offer some highly desirable features for landuse classification problems since they are able to take in a variety of data types, recorded on different statistical scales, and combine them. As such, neural networks should offer advantages of increased accuracy. However, a barrier to their general acceptance and use by all but `experts' is the difficulty of configuring the network initially. This paper describes the architectural problems of applying neural networks to landcover classification exercises in geography and details some of the latest developments from an ongoing research project aimed at overcoming these problems. A comprehensive strategy for the configuration of neural networks is presented, whereby the network is automatically constructed by a process involving initial analysis of the training data. By careful study of the functioning of each part of the network it is possible to select the architecture and initial weights on the node connections so the constructed network is `right first time'. Further adaptations are described to control network behaviour, to optimise functioning from the perspective of landcover classification. The entire configuration process is encapsulated by a single application which may be treated by the user as a `black box', allowing the network to the applied in much the same way as a maximum likelihood classifier, with no further effort being required of the user.

Keywords: Key words: Classification; neural networks; G15; JEL classification: C88; C63; C45; C44 (search for similar items in EconPapers)
Date: 1999
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://link.springer.com/10.1007/s101090050002 Abstract (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:kap:jgeosy:v:1:y:1999:i:1:d:10.1007_s101090050002

Ordering information: This journal article can be ordered from
http://www.springer. ... ce/journal/10109/PS2

DOI: 10.1007/s101090050002

Access Statistics for this article

Journal of Geographical Systems is currently edited by Manfred M. Fischer and Antonio Páez

More articles in Journal of Geographical Systems from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().