Clustering parameters selection algorithm based on density for divisional clustering process

被引：0

作者：

Wu Y. ^{[1
]}

Wang T. ^{[1
]}

Li J.-D. ^{[1
]}

机构：

[1] Department of Information Engineering, Ordnance Engineering College of PLA, Shijiazhuang

来源：

Kongzhi yu Juece/Control and Decision | 2016年 / 31卷 / 01期

关键词：

Clustering algorithm; Clustering center; Maximal-minimal distance; Relationship tree; Sample density;

D O I：

10.13195/j.kzyjc.2014.1592

中图分类号：

学科分类号：

摘要：

In order to select the initial clustering centers for the divisional clustering algorithm such as the K-means algorithm, the sample density calculating regions number of each dimension is confirmed according to the samples number and their values, firstly. Then, the average value of the samples of the region with peak value satisfying the filtering conditions is taken as the candidate for the initial clustering center, and a relationship tree of the candidates is established on the mapping relations of the regions. Furthermore, the initial clustering centers are selected by using the maximal-minimal distance algorithm. To confirm the best number of the clusters, a clustering quality evaluation function is established according to the sample density and cluster density. Experiment results of the manual and UCI data sets show the effectiveness of the proposed algorithms. © 2016, Editorial Office of Control and Decision. All right reserved.

引用

页码：21 / 29

页数：8

共 20 条

[1]

Xu R., Survey of clustering algorithm, IEEE Trans on Neural Networks, 16, 3, pp. 645-678, (2005)

[2]

Wang S.Q., Zhu D.M., Algorithm for the K-means clustering based on minimum cluster size, J of Communications, 31, 7, pp. 46-52, (2010)

[3]

Gelbard R., Goldman O., Spiegler I., Investigating diversity of clustering methods: An empirical comparison, Data & Knowledge Engineering, 63, 1, pp. 155-166, (2007)

[4]

Pilevar A.H., Sukumar M., GCHL: A grid-clustering algorithm for high-dimensional very large spatial data bases, Pattern Recognition Letters, 26, 7, pp. 999-1010, (2005)

[5]

Yu Y.Q., Zhao X.G., Wang G.R., Et al., An self-expanded clustering algorithm based on density units, Control and Decision, 21, 9, pp. 974-978, (2006)

[6]

Sun J.G., Liu J., Zhao L.Y., Clustering algorithms research, J of Software, 19, 1, pp. 48-61, (2008)

[7]

Likas A., Ulassis M., Uerbeek J., The global K-means clustering algorithm, Pattern Recognition, 36, 2, pp. 451-461, (2003)

[8]

Liu Y.M., Zhang H.X., Approach to selecting initial centers for K-means with variable threshold, Computer Engineering and Applications, 47, 32, pp. 56-58, (2011)

[9]

Xiong Z.Y., Chen R.T., Zhang Y.F., Effctive method for cluster' initialization in K-means clustering, Application Research of Computers, 28, 11, pp. 4188-4190, (2011)

[10]

Chen G.P., Wang W.P., Huang J., Improved initial clustering center selection method for K-means algorithm, J of Chinese Computer Systems, 33, 6, pp. 1320-1323, (2012)

← 1 2 →