An algorithm of spatial association rules mining used in mobile computing
TU Cheng-sheng · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2011
In order to fast mine spatial association rules and improve efficiency of mobile intelligent system, this paper proposes an algorithm of alternative search spatial association rules mining. The algorithm firstly uses the way of spatial buffer analysis to extract spatial predicate values, and then uses spatial predicate value of every target location to form a spatial transaction and turns it into integer by binary coding, finally uses iteration method of alternative search to extract spatial association rules, namely, not only does it use iteration method of gaining (L-1)-subset of L-non frequent itemsets to generate candidate frequent itemsets, it also uses iteration method of gaining (K+1)-superset of K-frequent itemsets to generate candidate frequent itemsets. The result of simulate experiment indicates that the algorithm is faster and more efficient than present mining algorithms when mining spatial association rules in mobile computing.