CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

id ddssup0213
authors Osaragi, Toshihiro
year 2002
title Classification Methods for Spatial Data Representation
source Timmermans, Harry (Ed.), Sixth Design and Decision Support Systems in Architecture and Urban Planning - Part two: Urban Planning Proceedings Avegoor, the Netherlands), 2002
summary In the process of representing quantitative spatial data on a map, it is necessary to classify attribute values into some class divisions. When a number of classes are employed, the characteristics of spatial distribution of original data can be expressed faithfully. However, its legends might become rather complicated and the delicate color differences in the represented map would be difficult to distinguish. On the other hand, when employing a few classes, the information such as small vibrating factors or local peaks might be ignored; namely, much information of original data will be lost. Hence, we should discuss how many classes are necessary to represent spatial data. Furthermore, even if the same spatial data are represented using the same number of classes, we might obtain the quite different maps according to the choice of classification methods incorporated in existing geographic information systems. Namely, the characteristics of the original data might be overlooked, or there might be a risk of mistaking judgment, if we do not have enough knowledge about classification methods as well as the nature of original data. Hence, we should also discuss how the boundary value between each class should be set. In this paper, a new classification method using an evaluation function based on Akaike’s Information Criterion is proposed, and is applied to actual spatial data. Next, based on the consideration about its result, another classification method minimizing information loss of original data is proposed. Furthermore, numerical examples of its applications are achieved through the comparison with existing classification methods.
series DDSS
full text file.pdf (724,758 bytes)
references Content-type: text/plain
details citation check to select
100%; open Akaike, H. (1972) Find in CUMINCAD Information theory and an extension of the maximum likelihood principle , Proceedings of the 2nd International Symposium on Information Theory, Akademiai kaido, Budapest (Eds B N Petron, F Csak) pp.267-281
100%; open Akaike, H. (1974) Find in CUMINCAD A new look at the statistical model identification , IEEE Transactions on Automatic Control 19, pp.716-723
100%; open Civco, D L. (1993) Find in CUMINCAD Artificial Neural networks for Land-cover Classification and Mapping , International Journal of Geographical Information Systems 7, pp.173-186
100%; open Erol, H. and Akdeniz, F. (1998) Find in CUMINCAD A new supervised classification method for quantitative analysis of remotely-sensed multi- spectral data , International Journal of Remote Sensing 19, pp.775-782
100%; open ESRI (1996) Find in CUMINCAD ArcView GIS – The Geographic Information System for Everyone , Environmental Systems Research Institute, USA
100%; open Flygare, A M. (1997) Find in CUMINCAD A Comparison of Contextual Classification Methods Using Landsat TM , International Journal of Remote Sensing 18, pp.3835-3842
100%; open Goodchild, M F., Guoqing, S. and Shiren, Y. (1992) Find in CUMINCAD Development and test of error model for categorical data , International Journal of Geographical Information Systems 6, pp.87-104
100%; open Higuchi, T., Tamagawa, H. and Ishak, A B P. (1988) Find in CUMINCAD A study on the optimum mesh size for continuous variables: An example by using a mental map , Papers on City Planning 23, pp.37-42. (in Japanese)
100%; open Jenks, G F. (1967) Find in CUMINCAD The Data Model Concept in Statistical Mapping , International Yearbook of Cartography 7, pp.186-190
100%; open Osaragi, T. (2001) Find in CUMINCAD Classification Methods for Spatial Data Representation , Working Paper 40, the Centre for Advanced Spatial Analysis, University College London, London
100%; open Osaragi, T. and Nakayama, H. (2000) Find in CUMINCAD Classification of Spatial Data in Visualization , Papers and Proceedings of the Geographic Information Systems Association 9, pp.361-366. (in Japanese)
100%; open Roy, J R., Batten, D F. and Lesse, P F. (1982) Find in CUMINCAD Minimizing information loss in simple aggregation , Environment and Planning A 14, pp.973-980
100%; open Shannon, C.E. (1948) Find in CUMINCAD A Mathematical Theory of Communication , Bell System Technical Journal 27, pp.379-423 and pp.623-656
100%; open Tamagawa, H. (1987) Find in CUMINCAD A study on the optimum mesh size in view of the homogeneity of land use ratio , Papers on City Planning 22, pp.229-234. (in Japanese)
100%; open Umesh, R M. (1988) Find in CUMINCAD A technique for cluster formation , Pattern Recognition 21, pp.393-400

last changed 2003/08/07 14:36
HOMELOGIN (you are user _anon_396302 from group guest) Works Powered by SciX Open Publishing Services 1.002