A fuzzy clustering model of data with proportional membership

The fuzzy clustering proportional membership (FCPM) proposes a model of how data are generated from a cluster structure to be identified. Cluster prototypes and membership functions are meaningful in the context of the model. In particular, the membership of an entity to a cluster expresses the proportion of the cluster's prototype reflected in the entity (proportional membership). We explore the notion of proportional membership and compare it against the fuzzy c-means (FCM) distance membership. The ability of FCPM to reveal the underlying clustering model of data has been studied and a comparison with FCM had also been performed.