DocumentCode :
1631800
Title :
Robust clustering algorithm for the symbolic interval-values data with outliers
Author :
Chuang, Chen-Chia ; Tao, Chin-Wang ; Jeng, Jin-Tsong
Author_Institution :
Dept. of Electr. Eng., Nat. Ilan Univ., Ilan, Taiwan
fYear :
2009
Firstpage :
1232
Lastpage :
1237
Abstract :
In this study, the novel robust clustering algorithm, robust interval competitive agglomeration (RICA) clustering algorithm, is proposed to overcome the problems of the outliers and the numbers of cluster in the competitive agglomeration clustering algorithm for the symbolic interval-values data. The Euclidean distance measure is considered in the proposed RICA clustering algorithm. Moreover, the RICA clustering algorithm can be fast converges in a few iterations regardless of the initial number of clusters. Additionally, the RICA clustering algorithm is also converges to the same optimal partition regardless of its initialization. Experimentally results show the merits and usefulness of the RICA clustering algorithm for the symbolic interval-values data.
Keywords :
pattern clustering; Euclidean distance measure; RICA clustering; competitive agglomeration clustering; optimal partition; robust clustering; robust interval competitive agglomeration; symbolic interval-values data; Clustering algorithms; Clustering methods; Couplings; Data analysis; Decision trees; Heuristic algorithms; Iterative algorithms; Partitioning algorithms; Prototypes; Robustness;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Fuzzy Systems, 2009. FUZZ-IEEE 2009. IEEE International Conference on
Conference_Location :
Jeju Island
ISSN :
1098-7584
Print_ISBN :
978-1-4244-3596-8
Electronic_ISBN :
1098-7584
Type :
conf
DOI :
10.1109/FUZZY.2009.5277425
Filename :
5277425
Link To Document :
بازگشت