Building new spatial interaction models by using genetic programming and a supercomputer.
Part of a special section on geocomputation, which is defined as the process of applying computing technology to geographical problems. The writer outlines an application of a parallel genetic programming approach to discovering new spatial interaction models. He discusses how to develop new models...
| Published in: | Environment & Planning A Vol. 30; no. 10; pp. 1893 - 1905 |
|---|---|
| Main Author: | |
| Format: | Article |
| Published: |
Pion Limited
October 1998
|
| Subjects: | |
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=512711248&site=ehost-live header: @attributes: shortDbName: ssf uiTerm: 512711248 longDbName: Social Sciences Full Text (H.W. Wilson) uiTag: AN controlInfo: bkinfo: jinfo: jid: 0308518X EPL jtl: Environment & Planning A issn: 0308518X maglogo: N pubinfo: dt: October 1998 vid: 30 iid: 10 pid: 1065 pub: Pion Limited artinfo: ui: 512711248 10.1068/a301893 ppf: 1893 ppct: 12 formats: tig: atl: Building new spatial interaction models by using genetic programming and a supercomputer. aug: au: Diplock, G. su: Computers Geography Mathematical geography Cray computers Parallel processing Geographic mathematics Geographic information systems sug: subj: Computers Geography Mathematical geography Cray computers Parallel processing Geographic mathematics Geographic information systems ab: Part of a special section on geocomputation, which is defined as the process of applying computing technology to geographical problems. The writer outlines an application of a parallel genetic programming approach to discovering new spatial interaction models. He discusses how to develop new models by means of a machine-based inductive approach. He employs a Cray T3D parallel supercomputer with 512 processors to examine the potential of this approach to building computer models. His findings allude to the potential power of the method for applications where a considerable amount of data exists but where there are no suitable existing models or no good theoretical framework on which to base their development. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: N holdings: @attributes: islocal: N |
|---|