属性加权FCM算法的参数选择规则

广西师范大学学报（自然科学版） ›› 2010, Vol. 28 ›› Issue (4): 42-48.

属性加权FCM算法的参数选择规则

李翠霞¹, 谭营军², 于剑³

1.郑州大学软件技术学院,河南郑州 450002;
2.河南职业技术学院信息工程系,河南郑州 450046;
3.北京交通大学计算机与信息技术学院,北京 100044

收稿日期:2010-07-22 发布日期:2023-02-07
通讯作者: 于剑(1969—),男,山东淄博人,北京交通大学教授,博士,博导。E-mail:jianyu@bjtu.edu.cn
基金资助:
国家自然科学基金资助项目(60875031);河南省科技攻关项目(102102210490)

Parameters Choosing of Attribute-Weighted Fuzzy C-means Algorithm

LI Cui-xia¹, TAN Ying-jun², YU Jian³

1.School of Software Technology,Zhengzhou University,ZhengzhouHenan 450002,China;
2.Department of Information Engineering,Henan PolyTechnic College,Zhengzhou Henan 450046,China;
3.School of Computer and Information Technology,Beijing Jiaotong University,Beijing 100082,China

Received:2010-07-22 Published:2023-02-07

摘要/Abstract

摘要： 属性加权FCM算法可在算法迭代过程中求出各属性的权值,并不影响算法本身的执行效率,可发现隐藏在部分属性中的类结构,提高分类准确率。鉴于参数对算法性能的影响,本文对该算法的目标函数进行了理论分析,通过严格的公式推导之后,给出了算法的参数选择规则。经实验证明,该规则对于属性加权FCM算法的参数选择有一定的指导作用。

关键词: 权值, 属性加权, 模糊指数, 模糊C均值聚类算法, 海森矩阵

Abstract: Attribute-Weighted Fuzzy C-means Algorithm mentioned in this paper may have different influence on each attribute with theiteration of objective function at the same time.It can find out the latent cluster structure without reducing the algorithm's efficiency.Considering the fact that parameters influence the results,this paper proposes a theoretic analysis based on the objective function of this algorithm.After strict formula derivation,this paper provides a parameters choosing rule.The experiments proved that this rule offersa parameters' choosing guideline to the AWFCM proposed in this paper.

Key words: weight, attribute weighted, fuzzy exponent, fuzzy C-means algorithm, Hessian matrix

中图分类号:

TP301.6

李翠霞, 谭营军, 于剑. 属性加权FCM算法的参数选择规则[J]. 广西师范大学学报（自然科学版）, 2010, 28(4): 42-48.

LI Cui-xia, TAN Ying-jun, YU Jian. Parameters Choosing of Attribute-Weighted Fuzzy C-means Algorithm[J]. Journal of Guangxi Normal University(Natural Science Edition), 2010, 28(4): 42-48.

参考文献

[1] HAN I,KAMBER M.Data mining:concepts and techniques[M].Berlin:Morgan Kaufmann Publishers,2000:335-389.
[2] YANG Miin-shen.A survey of fuzzy clustering[J].Math Comput Modelling,1993,18(11):1-16.
[3] JAIN A K,MURTY M N,FLYNN P J.Data clustering:a review[J].ACM Computing Surveys,1999,31(3):265-318.
[4] MACQUEEN J.Some methods for classification and analysis of multivariate observations[C]//Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability,Volume 1:Statistics.Berkeley,CA:University of CaliforniaPress,1967:281-297.
[5] BEZDEK J C.Pattern recognition with fuzzy objective function algorithms[M].New York:Plenum Press,1981.
[6] GREEN P E,CARMONE F J,KIM J.A preliminary study of optimal variable weighting in k-means clustering[J].J Classification,1990,7:271-285.
[7] DESARBO W S,CARROLL J D,CLARK L A,et al.Synthesized clustering:amethod foramalgamating clustering bases with differential weighting variables[J].Psychometrika,1984,49:57-78.
[8] SOETE G D.Optimal variable weighting for ultrametric and additivetree clustering[J].Quality and Quantity,1986,20(2/3):169-180.
[9] SOETE G D.OVWTRE:a program for optimal variable weighting for ultrametric and additive tree fitting[J].J Classification,1988,5:101-104.
[10] MODHA D S,Spangler W S.Feature weighting in k-means clustering[J].Machine Learning,2003,52:217-237.
[11] FRIEDMAN J H,MEULMAN J J.Clustering objects on subsets of attributes[J].J Royal Statistical Soc B,2004,66(4):815-849.
[12] HUANG Joshua Zhexue,NG M K,RONG Hong-qiang,et al.Automated variable weighting in k-means type clustering[J].IEEE Transactions on Pattern Analysisand Machine Intelligence,2005,27(5):657-668.
[13] 于剑.论模糊C均值算法的模糊指标[J].计算机学报,2003,26(8):968-973.
[14] YU Jian,CHENG Qian-sheng,HUANG Hou-kuan.Analysis of the weighting exponentin the FCM[J].IEEE Transactions on Systems,Man and Cybernetics-Part B:Cybernetics,2004,34(1):634-639.
[15] YU Jian,YANG Miin-shen.Optimality test for generalized FCM and its application to parameter selection[J].IEEE Transactions on Fuzzy Systems,2005,13(1):164-176.
[16] 于剑.聚类有效性及其应用[D].北京:北京大学数学科学学院,2000.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

本文评价

推荐阅读 10

[1]	陈永淇, 白克钊, 邝华, 孔令江, 刘慕仁. 教室内布局对人员疏散影响的研究[J]. 广西师范大学学报（自然科学版）, 2011, 29(1): 1 -4 .
[2]	许伦辉, 叶凡. 基于横、轴、竖加速度干扰模型的行车舒适性评价[J]. 广西师范大学学报（自然科学版）, 2011, 29(1): 5 -9 .
[3]	阳丽, 孔令江. 微纳米球形颗粒之间的毛细力研究[J]. 广西师范大学学报（自然科学版）, 2012, 30(1): 1 -4 .
[4]	贺青, 刘剑, 韦联福. 微弱电磁信号的物理极限检测:单光子探测器及其研究进展[J]. 广西师范大学学报（自然科学版）, 2022, 40(5): 1 -23 .
[5]	白克钊, 罗旭东, 孔令江, 刘慕仁. 开放边界条件下一种数据传输元胞自动机模型[J]. 广西师范大学学报（自然科学版）, 2010, 28(3): 1 -4 .
[6]	许伦辉, 廖燃火昆. 基于车流轨迹的交叉口相位相序优化[J]. 广西师范大学学报（自然科学版）, 2010, 28(3): 5 -9 .
[7]	王修信, 秦丽梅, 农京辉, 梁宗经, 朱启疆. 利用单窗算法反演喀斯特城市地表温度[J]. 广西师范大学学报（自然科学版）, 2010, 28(3): 10 -14 .
[8]	黎玉芳, 张军舰. NA样本回归函数估计的强相合性[J]. 广西师范大学学报（自然科学版）, 2010, 28(3): 15 -19 .
[9]	贾保华. 一个不满足中心极限定理的严平稳相伴随机序列[J]. 广西师范大学学报（自然科学版）, 2010, 28(3): 20 -23 .
[10]	陈翠玲, 李明, 梁家梅, 李略. Wolfe线搜索下一类新的共轭梯度法及其收敛性[J]. 广西师范大学学报（自然科学版）, 2010, 28(3): 24 -28 .