Collaborative fuzzy clustering

摘要

In this study, we introduce a new clustering architecture in which severl subsets of patterns can be processed to- gether with an objective of finding a structure that is common to all of them. To reveal this structure, the clustering algorithms operating on the separate subset of data collaborate by exchanging information about local partition matrices. In this sense, the required communication links are established at the level of information granules(more specifically, fuzzy sets forming the partition matrices)rather than patterns that are directly available in the databases. We discuss how this form of collaboration helps meet requirements of data confidentiality. A detailed clustering algo- rithm is developed on a basis of the standard FCM method and illustrated by means of numeric examples.