Research on uncertainty spatial association rule based on geo-rough space theory
Minshi Liu, Xiaofeng Hong, Dongyang Fang · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2009
A spatial association rule is a rule indicating certain association relationship among a set of spatial and possibly some non-spatial predicates. Most spatial data mining methods, including previous study on spatial association rules, use spatial objects with exactly known location. However, in real situations the extensions of spatial objects can be known only with a finite accuracy because of limits of measurement technology and uncertainties of objects et al. The inappropriate data mining methods based on these uncertain data will result in poor, even unaccepted quality of mining models. How to employ spatial association rule to extract hidden knowledge in uncertain and imprecise data is worth researching. Hence, in this paper we extend the technique for the discovery of spatial association rules from uncertainty data, based on geo-rough space theory. According to the concepts of the lower approximation set, the boundary set, rough topology relationships and rough distance relationships in geo-rough space, rough spatial predicates of Rough-Near, Rough-Touch, Rough-Overlay and Rough-In are proposed. Then we put forward more reasonable rough confidence and rough support for excavating spatial association rules from uncertainty data by using the Apriori algorithm. The result of case indicates the method works well.