The author investigates the extent to which smart computational methods can be used to create new and better performing types of spatial interaction model. He briefly describes the application of three different computationally intensive modelling technologies and compares the performance of the resulting models on a benchmark data set. It would appear that performance improvements of up to a factor of two can be obtained at the cost of a few orders of magnitude increase in compute times.
Get full access to this article
View all access options for this article.
References
1.
CareyH C, 1988Principles of Social Science first published in 1858 (J B Lipponcott, Philadelphia, PA)
2.
DiplockG J, 1996The Application of Evolutionary Computing Techniques to Spatial Interaction Modelling unpublished PhD thesis, School of Geography, University of Leeds, Leeds
FischerM MGopalS, 1994, “Artificial neural networks: A new approach to modelling interregional telecommunication flows”Journal of Regional Science34503–527
5.
FotheringhamA SWilliamsP A, 1985, “Destination choice and spatial competition in an urban hierarchy”, Department of Geography, University of Florida, Gainesville, FL
6.
GopalSFischerM M, 1996, “Learning in single hidden layer feed-forward network models”Geographical Analysis2838–55
KarrC L, 1991, “Genetic algorithms for fuzzy logic controllers”AI Expert626–33
9.
KnudsenD C, 1982, “An information theoretic approach for inferring individual cells of an interaction matrix from knowledge of marginal totals”, masters dissertation, Department of Geography, Indiana University, Bloomington, IN
10.
KnudsenD CFotheringhamA S, 1986, “Matrix comparison, goodness of fit, and spatial interaction modelling”International Regional Science Review10127–148
11.
KoskoB, 1992Neural Networks and Fuzzy Systems (Prentice-Hall, Englewood Cliffs, NJ)
12.
KoskoB, 1993, “Fuzzy systems as universal approximators”Proceedings of First IEEE International Conference on Fuzzy Systems (IEEE, San Diego, CA) pp 1153–1162
13.
KozaJ, 1992Genetic Programming: On the Programming of Computers by Means of Natural Selection (MIT Press, Cambridge, MA)
14.
LeungY, 1997Intelligent Spatial Decision Support Systems (Springer, Berlin)
15.
OpenshawS, 1976, “An empirical study of some spatial interaction models”Environment and Planning A823–41
16.
OpenshawS, 1988, “Building an automated modelling system to explore a universe of spatial interaction models”Geographical Analysis2031–46
17.
OpenshawS, 1993, “Modelling spatial interaction using a neural net”, in GIS, Spatial Modelling and Policy Eds FischerM MNijkampP, (Springer, Berlin) pp 147–164
18.
OpenshawS, 1994a, “Computational human geography: Towards a research agenda”Environment and Planning A26499–505
19.
OpenshawS, 1994b, “Computational human geography: Exploring the geocyberspace”Leeds Review37201–220
20.
OpenshawS, 1996, “Fuzzy logic as a new scientific paradigm for doing geography”Environment and Planning A28761–768
21.
OpenshawS, 1997, “Building fuzzy spatial interaction models”, in Advances in Spatial Analysis Eds GetisAFischerM M, (Springer, Berlin) pp 360–383
22.
OpenshawSConnollyC J, 1977, “Empirically derived deterrence functions for maximum performance spatial interaction models”Environment and Planning A91067–1079
23.
OpenshawSOpenshawC A, 1997Artificial Intelligence in Geography (John Wiley, Chichester, Sussex)
24.
OpenshawSGloverTClarkeG, 1998Spatial Interaction Modelling System (SIMS) CD-ROM (GeoInformation International, Cambridge)
25.
TakagiTSugenoM, 1985, “Fuzzy identification of systems and its application to modelling and control”IEEE Transactions on Systems, Man, Cybernetics15116–132
26.
ThomasR W, 1977, “An interpretation of the journey to work on Merseyside using entropy-maximising methods”Environment and Planning A9817–834
27.
TurtonIOpenshawSDiplockG J, 1997, “A genetic programming approach to building new spatial models relevant to GIS”, in Innovations in GIS 4 Ed. KempZ, (Taylor and Francis, London) pp 89–102
28.
WilsonA G, 1970Entropy in Urban and Regional Modelling (Pion, London)
29.
ZadehL A, 1992, “Foreword”, in Neural Networks and Fuzzy Systems (Prentice-Hall, Englewood Cliffs, NJ) pp xvii–xviii
