Title :
Revised PSK Clustering Algorithm
Author_Institution :
Fac. of Inst. of Operational Res. & Cybern., Hangzhou Dianzi Univ., Hangzhou, China
Abstract :
We present a new clustering algorithm (NPSK algorithm), based on the modification of the newly developed point symmetry-based K-means algorithm (PSK algorithm). Not only the proposed NPSK algorithm is suitable for almost all test data sets used by Chung and Liu for PSK algorithm , the proposed NPSK algorithm is also suitable for the case where the symmetric property of the data set is not so distinct. Experimental results demonstrate that our proposed NPSK algorithm is rather encouraging.
Keywords :
pattern clustering; statistical analysis; NPSK clustering algorithm; PSK clustering algorithm; data set; point symmetry-based K-means algorithm; statistical analysis; symmetric property; Clustering algorithms; Cybernetics; Image processing; Machine learning; Machine learning algorithms; Partitioning algorithms; Pattern recognition; Phase shift keying; Statistics; Testing;
Conference_Titel :
Wireless Communications, Networking and Mobile Computing, 2009. WiCom '09. 5th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-3692-7
Electronic_ISBN :
978-1-4244-3693-4
DOI :
10.1109/WICOM.2009.5305670
