Relational clustering based on a dissimilarity relation extracted from data by a TS model

Most clustering algorithmspartition a &fa set based on a dissimilarity relation expressed in t e m of some distance function. When the nature of this relation is conceptual rather than mehic, distance finctions may fail to adequately model dissimilarity. For this reason, we propose to extract dissimilarify relations directlyfrom the data. We exploit some pairs of paffems with known dissimilarity to build a T S f u q system which models the dissimilarity relation. Then, we use the TS @stem to compute a dissimilarity relation between any pair of panems. The resulting dissimilarity matrix is input to a new unsupervised f izzy relational clustering algorithm, which partitions the data set based on theproximity of the vectors containing the dissimilmity values between a p m e m and all the paffems in the data set. Experimental results to confirm the validity of our approach are shown and discussed