Cluster analysis based on fuzzy relations

Fuzzy Sets and SystemsPublished 1 June 2001

Miin‐Shen Yang, Hsing-Mei Shih

DOI10.1016/s0165-0114(99)00146-3

Source URL

Citations107

SJR quartileQ1

SJR score0.75

SNIP1.25

TL;DR

In this paper, cluster analysis based on fuzzy relations is investigated and Tamura’s max-min n-step procedure is extended to all types of max-t compositions, and the topic of incomplete data via max-T compositions is discussed.

Abstract

In this paper, cluster analysis based on fuzzy relations is investigated. Tamura's max-min n-step procedure is extended to all types of max-t compositions. A max-t similarity-relation matrix is obtained by beginning with a proximity-relation matrix based on the proposed max-t n-step procedure. Then a clustering algorithm is created for the max-t similarity-relation matrix. Three critical max-t compositions of max-min, max-prod and max-Δ are compared. The max-Δ composition is recommended as the first choice among them. Several examples give more perspectives for different choices of max-t compositions. Finally, the topic of incomplete data via max-t compositions is discussed. Max-t compositions can be effectively used to treat the t-connected incomplete data.

Keywords

Computer ScienceDecision Sciences

Fuzzy Set Theory—and Its Applications

7,484 Citations2001H.-J. Zimmermann

Information SciencesSimilarity relations and fuzzy orderings

2,621 Citations1971Lotfi A. Zadeh

An extended version of Szpilrajn's theorem is proved and various properties of similarity relations and fuzzy orderings are investigated and, as an illustration, a fuzzy preordering is investigated which is reflexive and antisymmetric.

Information and ControlA new approach to clustering

1,564 Citations1969Enrique H. Ruspini

A new method of representation of the reduced data, based on the idea of “fuzzy sets,” is proposed to avoid some of the problems of current clustering procedures and to provide better insight into the structure of the original data.

Mathematical and Computer ModellingA survey of fuzzy clustering

501 Citations1993Miin‐Shen Yang

A survey of fuzzy set theory applied in cluster analysis in three categories: the fuzzy clustering based on fuzzy relation, the fuzzy generalized k-nearest neighbor rule, and an overview of a nonparametric classifier.

Journal of Mathematical Analysis and ApplicationsAbstraction and pattern classification

424 Citations1966Richard Bellman, Robert E. Kalaba +1 more

A general framework for the treatment of pattern-recognition problems is discussed, including the notion of a 'fuzzy' set and how this may be employed in a sequential experimental procedure to ascertain whether a symbol is a member of a particular set or not.

Fuzzy Sets and SystemsFuzzy partitions and relations; an axiomatic basis for clustering

340 Citations1978James C. Bezdek, John Harris

A new definition of transitivity for fuzzy relations yields a relation-theoretic characterization of the class of all psuedo-metrics on a fixed data set into the closed unit interval.

IEEE Transactions on Systems Man and CyberneticsPattern Classification Based on Fuzzy Relations

291 Citations1971Shinichi Tamura, Seihaku Higuchi +1 more

A method of classifying patterns using fuzzy relations is described, where a similitude between any two patterns is calculated by using the composition of a fuzzy relation to induce an equivalence relation.

Pattern RecognitionGeneralized fuzzy c-shells clustering and detection of circular and elliptical boundaries

91 Citations1992Rajesh N. Davé

The AFCS algorithms consider hyper-ellipsoidal-shells as prototypes, hence the ability to characterize elliptical boundaries, and the generalization is achieved by allowing the distances to be measured through a norm inducing matrix that is symmetric, positive definite.

IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)On cluster-wise fuzzy regression analysis

81 Citations1997Miin‐Shen Yang, Cheng-Hsiu Ko

Numerical results give evidence that the one-stage procedure can be highly recommended in cluster-wise fuzzy regression analysis, which is used to overcome the heterogeneous problem in the fuzzy regression model.

Fuzzy Sets and SystemsFuzzy clustering algorithms based on the maximum likelihood priciple

79 Citations1991E. Trauwaert, L. Kaufman +1 more

By comparison between the hard and fuzzy methods it appears that the latter yield more often the global optimum, rather than merely a local optimum, than the former.