This paper presents a new approach to fuzzy clustering using a membership function sensitive to density. It is a fuzzy membership function which allows the action range of the neural units matching the area they reach, even when the data set is contaminated by uniformly distributed noise points, without a need to fix a priori the number of clusters
Density based membership function for fuzzy clustering / Acciani, G.; Caradonna, R.; Chiarantoni, E.; Grassi, G.. - STAMPA. - (1999), pp. 1140-1143. (Intervento presentato al convegno International Joint Conference on Neural Networks, IJCNN'99 tenutosi a Washington, DC nel July 10-16, 1999) [10.1109/IJCNN.1999.831118].
Density based membership function for fuzzy clustering
G. Acciani;E. Chiarantoni;
1999-01-01
Abstract
This paper presents a new approach to fuzzy clustering using a membership function sensitive to density. It is a fuzzy membership function which allows the action range of the neural units matching the area they reach, even when the data set is contaminated by uniformly distributed noise points, without a need to fix a priori the number of clustersI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
