5 November 2008 Study on urban land grading by evolutionary approaches to multi-objective spatial decision making
Author Affiliations +
Proceedings Volume 7144, Geoinformatics 2008 and Joint Conference on GIS and Built Environment: The Built Environment and Its Dynamics; 714429 (2008) https://doi.org/10.1117/12.812829
Event: Geoinformatics 2008 and Joint Conference on GIS and Built Environment: Geo-Simulation and Virtual GIS Environments, 2008, Guangzhou, China
Abstract
The results of Urban Land Grading reflect the differences of land quality among the cities. It takes a city as a point, and studies land quality under the influence of the various social, natural and economic conditions. The former classification of urban land is mainly depend on two method: Histogram Method and K-Means clustering analysis. But, both methods have clear limitations as follows: the method of Histogram Method depends on experts' experience, and the accuracy is not high; the method of K-Means clustering analysis mainly depends on attribute neighboring relations of city's grading scores, but neglects spatial distribution characteristics and geometry neighboring relations among cities. In this paper, we regard the city grading operation as a particular application of multi-objective spatial decision making problem, because it has both statistical object (within-grade homogeneity) and geographical object (equal-grade cities with geographical contiguity). And we adopt evolutionary approaches to resolve it.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yang Liu, Yang Liu, Yaolin Liu, Yaolin Liu, Zeying Lan, Zeying Lan, } "Study on urban land grading by evolutionary approaches to multi-objective spatial decision making", Proc. SPIE 7144, Geoinformatics 2008 and Joint Conference on GIS and Built Environment: The Built Environment and Its Dynamics, 714429 (5 November 2008); doi: 10.1117/12.812829; https://doi.org/10.1117/12.812829
PROCEEDINGS
9 PAGES


SHARE
Back to Top