Bezdek type fuzzy attribute C-means clustering algorithm
-
摘要: 推广了属性均值聚类算法,提出了基于模糊度m的Bezdek型模糊属性C均值聚类算法(FAMC),给出了FAMC算法的迭代算法,并讨论了模糊度m对算法收敛性的影响.在标准Iris数据集与肿瘤基因芯片表达数据的模式识别实验结果,验证了该算法优于模糊C均值算法和属性均值聚类算法.Abstract: Bezdek type fuzzy attribute C-means clustering algorithm(FAMC) was proposed by extending attribute means clustering(AMC) algorithm based on fuzziness index (or weighting exponent) m. The iterative algorithm was derived and the effect of fuzziness index m on objective function convergence was discussed. The experimental results of pattern recognition performances on standard Iris database and tumor/normal gene chip expression data demonstrate that FAMC is more effective than fuzzy C-means clustering(FCM) algorithm and AMC.
-
[1] Bezdek J C. Pattern recognition with fuzzy objective function algorithms[M]. New York:Plenum Press, 1981 [2] Pal N R, Bezdek J C. On cluster validity for the fuzzy C-means model [J]. IEEE Trans Syst, 1995,3(3):370- 379 [3] Dembele D, Kastner P. Fuzzy C-means method for clustering microarray data[J]. Bioinformatics, 2003, 19(8):973- 980 [4] Karayiannis N B. Weighted fuzzy learning vector quantization and weighted generalized fuzzy C-means algorithms IEEE International Conference on Fuzzy Systems. :IEEE, 1996, 2:773-779 [5] 程乾生.属性均值聚类[J].系统工程理论与实践, 1998, 18(9):124-126 Cheng Qiansheng. Attribute means clustering[J]. Systems Engineering-Theory & Practice, 1998,18(9):124-126 (in Chinese) [6] Yang Y, Zheng C X, Lin P. Image thresholding based on spatially weighted fuzzy C-means clustering The Fourth International Conference on Computer and Information Technology (CIT'04). :IEEE Computer Society, 2004, 184-189 [7] 高新波,李洁,姬红兵.基于加权模糊c均值聚类与统计检验指导的多阈值图像自动分割算法[J].电子学报, 2004, 32(4):661-664 Gao Xinbo, Li Jie, Ji Hongbing. A multi-threshold image segmentation algorithm based on weighting fuzzy C-means clustering and statistical test[J]. Acta Electronica Sinica, 2004, 32(4):661-664 (in Chinese) [8] 彭春华,程乾生.一种基于最小张树的属性聚类算法[J].系统工程理论与实践, 2001,21(2):30-34 Peng Chunhua, Cheng Qiansheng. An attribute clustering algorithm based on minimum spanning tree [J]. Systems Engineering Theory & Practice, 2001, 21(2):30-34 (in Chinese) [9] 苏勇,王士同,吴小俊,等. 属性-计混合聚类算法研究[J].计算机工程与应用,2001, 37(19):90-91 Su Yong, Wang Shitong, Wu Xiaojun, et al. A study on attribute-statistical hybrid clustering algorithm[J]. Computer Engineering and Applications, 2001, 37(19):90-91 (in Chinese) [10] 贺仁亚, 程乾生.一种新的分类方法[J].数学的实践与认识, 2002, 32(5):830-834 He Renya, Cheng Qiansheng. A new classification method[J]. Mathematics in Practice and Theory, 2002, 32(5):830- 834 (in Chinese) [11] 张媛祥.一种稳健的聚类方法[J].数学的实践与认识, 2003,33(8):8-10 Zhang Yuanxiang. A kind of robust clustering methods[J]. Mathematics in Practice and Theory, 2003, 33(8):8-10 (in Chinese) [12] 高新波.模糊聚类分析及其应用[M].西安:西安电子科技大学出版社, 2004 Gao Xinbo. Fuzzy cluster analysis and its application[M]. Xi'an:XiDian University Press, 2004 (in Chinese) [13] Ben-Dor A, Bruhn L, Friedman N, et al. Tissue classification with gene expression profiles Proceeding of the Fourth Annual International Conference on Computational Molecular Biology (Recomb 2000). Tokyo:ACM Press, 2000, 54-64 [14] 高新波,李洁.模糊C均值聚类算法中参数m的优选[J].模式识别与人工智能, 2000,13(1):7-11 Gao Xinbo, Li Jie. Optimal choice of weighting exponent in a fuzzy C-means clustering algorithm[J]. Pattern Recognition and Artificial Intelligent, 2000, 13(1):7-11 (in Chinese) [15] 高新波, 裴继红, 谢维信. 模糊C-均值聚类算法中加权指数m的研究[J]. 电子学报, 2000,28(4):80-83 Gao Xinbo, Pei Jihong, Xie Weixin. A study of weighting exponent m in a fuzzy C-means algorithm[J]. Acta Electronica Sinica, 2000,28(4):80-83 (in Chinese) [16] 于剑.论模糊C均值算法的模糊指标.计算机学报[J]. 2003,26(8):965-973 Yu Jian. On the fuzziness index of the FCM algorithms [J]. Chinese Journal of Computers, 2003, 26(8):965- 973(in Chinese)
点击查看大图
计量
- 文章访问数: 3485
- HTML全文浏览量: 123
- PDF下载量: 1254
- 被引次数: 0