Cluster analysis based in fuzzy relations
Fuzzy Sets and Systems - Special issue on clustering and learning
Logic-oriented fuzzy clustering
Pattern Recognition Letters
Clustering with a minimum spanning tree of scale-free-like structure
Pattern Recognition Letters
A clustering method based on fuzzy equivalence relation for customer relationship management
Expert Systems with Applications: An International Journal
Hi-index | 0.05 |
A problem of the optimal approximation to a fuzzy tolerance relation is discussed in this paper. Specifically, our aim is to get the optimal fuzzy equivalence relation from a given fuzzy tolerance relation. Firstly, we discuss the relationship between the covering and the partition of a set. Then, we give the concept of distance between coverings (or partitions) and put forward the algorithms to get the optimal partition from a given covering. Main results include: 1) give the sufficient and necessary conditions for the optimal approximation of coverings in union sets; 2) give the necessary condition for absolutely optimal approximation of coverings; 3) based on the optimal approximation of each covering in the covering chain, the optimal fuzzy equivalence relation is obtained from the given fuzzy tolerance relation.