DocumentCode :
460676
Title :
A Possibilistic C-Means Clustering Algorithm Based on Kernel Methods
Author :
Wu, Xiao-Hong
Author_Institution :
Coll. of Electr. & Inf. Eng., Jiangsu Univ., Zhenjiang
Volume :
3
fYear :
2006
fDate :
25-28 June 2006
Firstpage :
2062
Lastpage :
2066
Abstract :
A novel fuzzy clustering algorithm, called kernel possibilistic c-means model (KPCM), is proposed. KPCM algorithm is based on kernel methods and possibilistic c-means (PCM) algorithm and it is the extension of PCM algorithm. Different from PCM and FCM which are based on Euclidean distance, the proposed model is based on kernel-induced distance by using kernel methods. Furthermore, with kernel methods the input data can be mapped implicitly into a high-dimensional feature space where possibilistic c-means clustering is carried out. FCM, PCM and KPCM are performed numerical experiments on data sets. The experimental results show the better performance of KPCM
Keywords :
fuzzy set theory; pattern clustering; KPCM algorithm; fuzzy clustering algorithm; high-dimensional feature space; kernel possibilistic c-means model; kernel-induced distance; Algorithm design and analysis; Clustering algorithms; Educational institutions; Fuzzy set theory; Fuzzy sets; Information science; Kernel; Partitioning algorithms; Phase change materials; Space technology;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Communications, Circuits and Systems Proceedings, 2006 International Conference on
Conference_Location :
Guilin
Print_ISBN :
0-7803-9584-0
Electronic_ISBN :
0-7803-9585-9
Type :
conf
DOI :
10.1109/ICCCAS.2006.285084
Filename :
4064310
Link To Document :
بازگشت