Fuzzy multisets and fuzzy clustering of documents

Aims at developing a method of fuzzy clustering based on fuzzy multisets. Data clustering has been discussed in relation to information retrieval models and fuzzy multisets provide an appropriate model of information retrieval on the WWW. Fuzzy clustering of fuzzy multisets is thus necessary for application to an information retrieval model. A term-document matrix in which entries are multisets are considered. Two dissimilarity measures on fuzzy multisets are proposed. Two methods of fuzzy c-means using these measures are studied in which calculation of cluster centers is focused upon.