A Clustering Algorithm Based on Improved Particle Swarm Optimization

Abstract:

K-means algorithm is a traditional cluster analysis method, has the characteristics of simple ideas and algorithms, and thus become one of the commonly used methods of cluster analysis. However, the K-means algorithm classification results are too dependent on the choice of the initial cluster centers for some initial value, the algorithm may converge in general suboptimal solutions. Analysis of the K-means algorithm and particle swarm optimization based on a clustering algorithm based on improved particle swarm algorithm. The algorithm local search ability of the K-means algorithm and the global search ability of particle swarm optimization, local search ability to improve the K-means algorithm to accelerate the convergence speed effectively prevent the occurrence of the phenomenon of precocious puberty. The experiments show that the clustering algorithm has better convergence effect.

• Periodical: Applied Mechanics and Materials (Volumes 635-637)
• Pages: 1467-1470
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.635-637.1467
• Online since: September 2014
• Authors: Xun Wang
• Keywords: Algorithm K-Means, Cluster Analysis, Convergence Rate, Globally Optimal, Particle Swarm Algorithm

References

[1] Recognition of Corners of Planar Checkboard Calibration Pattern Image[A]; Proceedings of 2010 Chinese Control and Decision Conference[C]; (2010).

DOI: 10.1109/ccdc.2010.5498608

[2] Identification of QR Codes Based on Pattern Recognition[A]; Computer and Computing Technologies in Agriculture-Ⅱ-Proceedings of the Third IFIP International Conference on Computer and Computing Technologies in Agriculture(CCTA 2009)[C]; (2009).

[3] Symmetrical 2DLDA using Different Measures in Face Recognition[A]; Proceedings of 2009 Second International Workshop on Knowledge Discovery and Data Mining[C]; (2009).

DOI: 10.1109/wkdd.2009.195

[4] Support Vector Machines for Multi-Class Pattern Recognition Based on Improved Voting Strategy [A]; Proceedings of 2010 Chinese Control and Decision Conference[C]; (2010).

DOI: 10.1109/ccdc.2010.5499000

[5] A Recognition Method of Apples Based on Texture Features and EM Algorithm[A]; Computer and Computing Technologies in Agriculture-Ⅱ-Proceedings of the Third IFIP International Conference on Computer and Computing Technologies in Agriculture(CCTA 2009)[C]; (2009).