Share Email Print

Proceedings Paper

Formalizing natural-language spatial relations descriptions with fuzzy decision tree algorithm
Author(s): Jun Xu; Changqing Yao
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

People usually use qualitative terms to express spatial relations, while current geographic information systems (GIS) all use quantitative approaches to store spatial information. The abilities of current GIS to represent and query spatial information about geographic space are limited. In order to incorporate the concepts and methods people use to infer information about geographic space into GIS, research on the formal model of common sense geography becomes increasingly important. Previous research on the formalizations of natural-language descriptions of spatial relations are all based on crisp classification algorithms. But the human languages about spatial relations are ambiguous. There is no clear boundary between "yes" or "no" if a spatial relation predicate can express the spatial relations between objects. So the results of crisp classification algorithms can not formalize natural-language terms well. This paper uses a fuzzy decision tree method to formalize the spatial relations between two linear objects. Topologic and metric indices are used as variables, and the results of a human-subject test are used as training data. The formalization result of the fuzzy decision tree is compared with the result of a crisp decision tree.

Paper Details

Date Published: 28 October 2006
PDF: 10 pages
Proc. SPIE 6420, Geoinformatics 2006: Geospatial Information Science, 64201E (28 October 2006); doi: 10.1117/12.712745
Show Author Affiliations
Jun Xu, Institute of Geographic Science and Natural Resources Research (China)
Changqing Yao, Institute of Scientific and Technical Information of China (China)

Published in SPIE Proceedings Vol. 6420:
Geoinformatics 2006: Geospatial Information Science
Jianya Gong; Jingxiong Zhang, Editor(s)

© SPIE. Terms of Use
Back to Top