An Improved Initial Clustering Center Selection Method for K-Means Algorithm

Hong Bo Zhou; Jun Tao Gao

doi:10.4028/www.scientific.net/AMR.1022.337

Paper Titles

Topology Analysis for the Damaged Road Network Based MapX
p.321

Information Processing in Design and Testing of Financial Early Warning Method of Listed Companies in China - Based on the Logistic Regression Analysis
p.325

Applied-Information Technology in Design of Diabetic Rehabilitation Management System Based on the Technology of Mobile Internet
p.329

Applied Technology in Data Evaluation and Position Quality of ADS-B System
p.333

An Improved Initial Clustering Center Selection Method for K-Means Algorithm
p.337

Technology Study on the Perception of Stereopsis in Fovea Field
p.341

Research on the Monitoring of Internet with Public Opinions Based on Micro-Blog in Universities
p.345

The Teaching Web-Site Building of Technician Certificate for Electronic Elements Soldering and Taking Apart
p.349

Research on Information Technology in Effective Class Activities with Effective Class Measures
p.353

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 1022An Improved Initial Clustering Center Selection...

An Improved Initial Clustering Center Selection Method for K-Means Algorithm

Abstract:

Clustering result is easily influenced by the initial clustering centers in the K-means algorithm,an improved algorithm about initial clustering centers selection is presented.The algorithm finds the maximun Euclidean distance of cluster firstly,and then makes the cluster to split by used two data objects which have the maximum distance as new clustering centers,repeat the above steps until the specified number of clustering centers are obtained.Compared to the original algorithm,the improved algorithm can solve the problem of the instability of clustering effect generated by randomness, and its time complexity was also decreased.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 1022)

Pages:

337-340

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.1022.337

Citation:

Cite this paper

Online since:

August 2014

Authors:

Hong Bo Zhou*, Jun Tao Gao

Keywords:

Cluster Centers, Euclidean Distance, K-Means Algorithm, Sum of Squared Error

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] MacQueen J. Some methods for classification and analysis of multivariate observations[C]. Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability. Berkeley: University of California Press, 1967: 281-297.

Google Scholar

[2] Jain A K, Dubes R C. Algorithms for Clustering Data. Englewood Cliffs, NJ, USA: Prentice-Hall, (1988).

Google Scholar

[3] Xu R, Wunsch D. Survey of clustering algorithm. IEEE Trans. Neural Networks, 2005, 16(3): 645-678.

Google Scholar

[4] Laszlo M, Mukherjee S. A Genet ic Algorithm Th at Exchanges Neighboring Cent ers for K -Means Clustering [J]. Pattern Recogni tion Letters, 2007, 28(16): 2359-2366.

DOI: 10.1016/j.patrec.2007.08.006

Google Scholar

[5] Likas A, Vl assis N, Verbeek J. The Global K–means Clustering Algorithm[J]. Pat ter n Recogni tion, 2008, 36(2): 451-461.

Google Scholar

[6] UCI Repository of machine learning databases and domain theories[EB/OL]. FTP address: ftp: /ftp. ics. uc. i edu/pub /machine-learning-databases.

Google Scholar