Title :
Fuzzy type-2 c-ellipses clustering
Author :
Golsefid, S. MalekMohamadi ; Zarandi, M.H.F. ; Bastani, Saeed
Author_Institution :
Dept. of Ind. Eng., Amirkabir Univ. of Technol., Tehran, Iran
Abstract :
In this paper, a new prototype for fuzzy type-2 clustering is proposed. The proposed model considers ellipsoid shape for clusters and ellipsoid focal vectors are basis for measuring the distance from clusters, instead of cluster centers. Therefore, the degrees of belonging to clusters are defined as interval fuzzy type-2 sets indicated by the upper and lower membership values. The results of proposed model on the sample data sets are compared with fuzzy c-ellipsoid clustering algorithms.
Keywords :
fuzzy set theory; pattern clustering; vectors; ellipsoid focal vectors; ellipsoid shape; fuzzy type-2 c-ellipse clustering; interval fuzzy type-2 sets; lower membership values; upper membership values; Clustering algorithms; Ellipsoids; Linear programming; Mathematical model; Prototypes; Shape; Uncertainty;
Conference_Titel :
IFSA World Congress and NAFIPS Annual Meeting (IFSA/NAFIPS), 2013 Joint
Conference_Location :
Edmonton, AB
DOI :
10.1109/IFSA-NAFIPS.2013.6608575