Algorytm klasyfikacji rozmytej dla obiektów opisanych za pomocą zmiennych symbolicznych oraz rozmytych
Fuzzy clustering algorithm for objects described by symbolic or fuzzy variables

Summary/Abstract: The majority of discussed classification methods allow to cluster objects described by variables of the same type. In real applications many objects can be characterized by mixed feature types. The aim of this work is to present fuzzy clustering algorithm for objects, which can be described at the same time by numerical, symbolic and fuzzy data. This algorithm was presented by Yang, Hwang and Chen, who defined dissimilarity measure between objects represented by mixed features and they modified fuzzy c-means algorithm. This article also includes a numerical example based on real data, which illustrates the application of this method for objects with mixed features.

• Details
• Contents