DECISION ANALYSIS OF FUZZY PARTITION TREE APPLYING FUZZY THEORY

We often use fuzzy graph to analyze inexact information such as sociogram structure ([1,2]). Concerning the hierarchical cluster analysis of a fuzzy graph ([3-5] and [1]), the number of clusters may have to be decided in the actual cluster analysis. In other word, we would like to decide the optimal level with a partition tree. Concerning this problem, the steepest decent method in the multivariate analysis and AIC method in the statistical analysis have been designed by us ([6,10]). But, the steepest decent method could produce local limited solution problem and AIC method which is reasonablely based on the statistical inference needs a lot of samples. For these reasons, we would propose the evaluation method based on Fuzzy Decision which could obtain the optimal level even if there are not so many samples. In this paper, we would proceed to explain the practical effectiveness of our method through the cases in sociometry analysis.