Paper:
Language: English:

Quantification of Multivariate Categorical Data Considering Typicality of Item

Chi-Hyon Oh^*, Katsuhiro Honda^, and Hidetomo Ichihashi^

^*Faculty of Liberal Arts and Sciences, Osaka University of Economics and Law, 6-10 Gakuonji, Yao, Osaka 581-8511, Japan
^**Graduate School of Engineering, Osaka Prefecture University, 1-1 Gakuen-cho, Nakaku, Sakai, Osaka 599-8531, Japan

Received: October 31, 2005

Accepted: March 31, 2006

Keywords: fuzzy clustering, homogeneity analysis, multivariate categorical data

Journal ref: Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.11, No.1 pp. 35-39, 2007

Abstract

We propose simultaneously applying homogeneity analysis and fuzzy clustering that simultaneously partitions individuals and items in categorical multivariate datasets. This objective function includes two types of memberships. One is conventional membership representing the degree of membership of each individual in each cluster. The other is an additional parameter that represents typicality of item. A numerical experiment demonstrates that our proposal is useful in quantifying categorical data, taking the typicality of each item into account.

[Notice]
* "Preview" is the first 2 pages of the article. You don't need the registration.
* To read the PDF file you will then need to download and install the Adobe Reader.
Adobe Reader is free and available for download here: