关键词: 层次分析法, 模糊等价关系, 加权空间模糊动态聚类, 最佳分类

Abstract: Generally the spatial fuzzy clustering algorithm has not differentiated the imbalance between the various attributes and discussed the best classification number.In response to this problem，this paper uses a spatially weighted fuzzy dynamic clustering algorithm.First，the weight of each attribute is accessed using AHP；and then weight is added to the spatial fuzzy dynamic clustering algorithm；finally，the F-distribution of probability statistics is used to determine the best classification number，in order to improve the algorithm’s intelligence.This algorithm is compared with the transitive closure algorithm based on fuzzy equivalent relations.Tests show that the clustering algorithm’s accurate rate is higher than not weighted fuzzy clustering algorithm.

Key words: analytic hierarchy process, fuzzy equivalence relat