Title :
Linear fuzzy clustering based on least absolute deviations
Author :
Honda, Katsuhiro ; Togo, Nobuhiro ; Fujii, Taro ; Ichihashi, Hidetomo
Author_Institution :
Graduate Sch. of Eng., Osaka Prefecture Univ., Japan
fDate :
6/24/1905 12:00:00 AM
Abstract :
This paper proposes a technique of linear fuzzy clustering based on least absolute deviations. The novel method partitions a data set into several linear clusters by extracting local minor components. Using the least absolute deviations, the method provides robust clustering that is free from the influences of outliers
Keywords :
fuzzy set theory; pattern clustering; data set partitioning; least absolute deviations; linear fuzzy clustering; local minor component extraction; outliers; robust clustering; Clustering algorithms; Clustering methods; Data mining; Eigenvalues and eigenfunctions; Fuzzy sets; Principal component analysis; Prototypes; Robustness; Scattering; Vectors;
Conference_Titel :
Fuzzy Systems, 2002. FUZZ-IEEE'02. Proceedings of the 2002 IEEE International Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7280-8
DOI :
10.1109/FUZZ.2002.1006717
