2005 Volume 17 Issue 2 Pages 147-156
Conventionally, fuzzy multivariate data analysis has been proposed along with the issue of positively introducing uncertainty in real data and the methodology itself. Fuzzy Clustering is one method which can capture the uncertainty situation of real data and it is well known that fuzzy clustering can obtain a robust result as compared with conventional hard clustering. Following along with the emphasis on the general problem of data analysis, which is a solution for analyzing a huge amount of complex data, the merit of fuzzy clustering for this is expected. In this paper, we describe fuzzy clustering methods, which are methods in fuzzy multivariate analysis, along with several hybrid methods of fuzzy clustering and conventional multivariate analysis which have recently been proposed by us based on the idea that the multiple merits of methods can cope with the inherent classification structures.