doi:

DOI: 10.3724/SP.J.1001.2009.03410

Journal of Software (软件学报) 2009/20:11 PP.2939-2949

Fuzzy Maximum Scatter Difference Discriminant Criterion Based Clustering Algorithm


Abstract:
In this paper, a fuzzy scatter difference discrimininant criterion is presented. Based on this criterion, fuzzy clustering algorithm FMSDC (fuzzy maximum scatter difference discriminant criterion based clustering algorithm) is also presented. The proposed algorithm reduces dimensionality while clustering by iterative optimizing procedure. First, it introduces the fuzzy concept into maximum scatter difference discriminant criterion; then the parameter h in the fuzzy criterion is appropriately determined based on specific principles so that the sensibility aroused by parameter h can be decreased to some extent; At last clustering and reducing dimensionality are realized according to fuzzy membership mik and optional discriminant vector w, respectively. Experimental results demonstrate the proposed method FMSDC is not only capable of clustering but also robust and capable of reducing dimensionality.

Key words:fuzzy maximum scatter difference discriminant criterion,discriminant vector,dimensionality reduction,fuzzy clustering,robust

ReleaseDate:2014-07-21 14:52:02

Funds:Supported by the National Natural Science Foundation of China under Grant Nos.60773206, 60903100, 90820002 the National High-Tech Research and Development Plan of China under Grant Nos.2007AA1Z158, 2006AA10Z313 the National Defense Research Foundation of China under Grant No.A1420461266 the Jiangsu Provincial Innovation Project of Graduate Students of China under Grant No.CX09B-175Z the Open Project Program of the State Key Laboratory of CAD&CG, Zhejiang University of China under Grant No.A0802



[1] Wang XZ, Wang YD, Wang LJ. Improving fuzzy c-means clustering based on feature-weight learning. Pattern Recognition Letters, 2004,25(4):1123-1132.

[2] Yu J, Li CX. Novel cluster validity index for FCM algorithm. Journal of Computer Science and Technology, 2006,21(1):137-140.

[3] Yu J. General C-means clustering model. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2005,27(8):1197-1211.

[4] Gao G, Wu J. A convergence theorem for the fuzzy subspace clustering (FSC) algorithm. Pattern Recognition, 2008(14): 1939-1947.

[5] Karayiannis NB. An axiomatic approach to soft learning vector quantization and clustering. IEEE Trans. on Neural Networks, 1999, 10(5):1153-1165.

[6] Karayiannis NB. Soft learning vector quantization and clustering algorithms based on ordered weighted aggregation operators. IEEE Trans. on Neural Networks, 2000,11(5):1093-1105.

[7] Karayiannis NB, Bezdek JC. An integrated approach to fuzzy learning vector quantization and fuzzy c-means clustering. IEEE Trans. on Fuzzy Systems, 1997,5(4):622-628.

[8] Chung KL, Lin JS. Faster and more robust point symmetry-based K-means algorithm. Pattern Recognition, 2007,40(2):410-422.

[9] Sun JG, Liu J, Zhao LY. Clustering algorithm research. Journal of Software, 2008,19(1):48-61 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/19/48.htm 孙吉贵,刘杰,赵连宇.聚类分析.软件学报,2008,19(1):48-61. http://www.jos.org.cn/1000-9825/19/48.htm

[10] Rouseeuw PJ, Kaufman L, Trauwaert E. Fuzzy clustering using scatter matrices. Computational Statistics & Data Analysis, 1996, 23(4):135-151.

[11] Krishnapuram R, Kim J. Clustering algorithms based on volume criteria. IEEE Trans. on Fuzzy Systems, 2000,8(2):228-236.

[12] Gath I, Geva AB. Unsupervised optimal fuzzy clustering. IEEE Trans. on Pattern Analysis Machine Intelligence, 1989,11(7): 773-781.

[13] Wu KL, Yu J, Yang MS. A novel fuzzy clustering algorithm based on a fuzzy scatter matrix with optimality tests. Pattern Recognition Letters, 2005,26(10):639-652.

[14] Song FX, Cheng K, Yang JY, Liu SH. Maximum scatter difference, large margin linear projection and support vector machines. Acta Automatica Sinica, 2004,30(6):890-896 (in Chinese with English abstract). 宋枫溪,程科,杨静宇,刘树海.最大散度差和大间距线性投影与支持向量机.自动化学报,2004,30(6):890-896.

[15] Song FX, Zhang D, Yang JY, Gao XM. Adaptive classification algorithm based on maximum scatter difference discriminant criterion. Acta Automatica Sinica, 2006,32(4):541-549 (in Chinese with English abstract). 宋枫溪,张大鹏,杨静宇,高秀梅.基于最大散度差鉴别准则的自适应分类算法.自动化学报,2006,32(4):541-549.

[16] Bian ZQ, Zhang XG. Pattern Recognition. 2nd ed., Beijing: Tsinghua University Press, 2001 (in Chinese). 边肇祺,张学工.模式识别.第2版,北京:清华大学出版社,2001.

[17] Franc V, Hlavac V. Statistical pattern recognition toolbox. 2003. http://cmp.felk.cvut.cz/cmp/software/stprtool

[18] Ideker T, Thorsson V, Ranish JA, Christmas R, Buhler J, Eng JK, Bumgarner RE, Goodlett DR, Aebersold R, Hood L. Integrated genomic and proteomic analyses of a systemically perturbed metabolic network. Science, 2001,292(5):929-934.

[19] Yang CM, Wan BK, Gao XF. Selection of data preprocessing methods and similarity metrics for gene cluster analysis. Progress in Natural Science, 2006,16(6):607-613.

[20] Trygve R. Brodatz textures. 2006. http://www.ux.uis.no/~tranden/brodatz.html

[21] Chung FL, Wang ST, Deng ZH, Shu C, Hu D. Clustering analysis of gene expression data based on semi-supervised clustering algorithm. Soft Computing, 2006,10(5):981-993.

PDF