期刊文献+

基于D-S证据理论的模糊聚类集成 被引量:8

Fuzzy clustering ensemble based on DS theory
下载PDF
导出
摘要 针对现有集成方法在处理模糊聚类时的不足,提出一种新的模糊聚类集成方法。在证据合成的理论框架内,讨论在识别框架、概率分配函数、合成规则等问题。给出了3种基本概率分配方法:近似类别分配概率方法、归一化模糊海明距离方法以及二者证据合成的方法。分析指出合成的方法能够较好利用二者的优势进行互补,获取更为合理的基本概率分配方法。最后,通过实验讨论所提方法的参数设置、收敛性和有效性等问题。 In order to overcome the weakness of present ensemble methods for fuzzy clustering,a novel method of fuzzy clustering ensemble is proposed.In the framework of evidence ensemble,the recognition framework,basic probability assignment and synthesis rules are analyzed.Three different basic probability assignment(BPA)methods is proposed,which are approximation probability of clusters,normalized fuzzy Hamming distance,and evidence synthesis of the two.Because of complementary advantages of the two methods,the third method is able to get more useful BPA.At last,parameter settings,convergence and effectiveness of the method proposed are analyzed by experiment.
出处 《系统工程与电子技术》 EI CSCD 北大核心 2014年第7期1446-1452,共7页 Systems Engineering and Electronics
基金 国家自然科学基金(60975026 61273275)资助课题
关键词 模糊聚类集成 D-S证据理论 互相关矩阵 模糊海明距离 fuzzy clustering ensemble Dempster-Shafer theory co-association matrix fuzzy hamming distance
  • 相关文献

参考文献18

  • 1Fred A L N, Jain A K. Combining multiple clusterings using ev- idence accumulation[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2005, 27(6):835-850.
  • 2卢志茂,李纯,张琦.近邻传播的文本聚类集成谱算法[J].哈尔滨工程大学学报,2012,33(7):899-905. 被引量:9
  • 3许晓丽,卢志茂,张格森,李纯,张琦.改进近邻传播聚类的彩色图像分割[J].计算机辅助设计与图形学学报,2012,24(4):514-519. 被引量:27
  • 4Schapire R E. The Strength of weak Learn abilityEJ]. Machine Learning, 1990, 5(2): 197-227.
  • 5Susnjak T, Barczak A, Reyes N, et al. A new ensemble based cascaded framework for muhiclass training with simple weak learners[J]. Lecture Notes in Computer Science, 2011, 6854 (1): 563-570.
  • 6Dietterich T G. An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and ran domization[J]. Machine Learning, 2000,40(2) : 139 - 157.
  • 7Oliveira L S, Morita M, Sabourin R. Multi-objective genetic al gorithm create ensemble of classifiers[C://Proc, of the Third International Conference on Evolutionary Multi-Criterion Opti- mization, 2005:592 - 606.
  • 8Fred A L N. Finding consistent clusters in data partitions[J]. Lecture Notes in Computer Science, 2001, 2096(1) : 309 - 318.
  • 9Fred A L N, Jain A K. Data clustering using evidence accumula- tion[C://Proc, of the 16th International Conference on Pattern Recognitio, 2002:276 - 280.
  • 10Strehl A, Ghosh J. Cluster ensembles a knowledge reuse frame- work for combining partitionings[C]//Proc of the Association for the Advancement of Artificial Intelligence, 2002 : 93 - 98.

二级参考文献35

  • 1唐伟,周志华.基于Bagging的选择性聚类集成[J].软件学报,2005,16(4):496-502. 被引量:95
  • 2TIAN Zheng,LI XiaoBin,JU YanWei.Spectral clustering based on matrix perturbation theory[J].Science in China(Series F),2007,50(1):63-81. 被引量:19
  • 3罗会兰,孔繁胜,李一啸.聚类集成中的差异性度量研究[J].计算机学报,2007,30(8):1315-1324. 被引量:36
  • 4Tan P N,Steinbach M,Kumar V.Introduction to Data Mining.MA,USA:Addison-Wesley,2005.487-647.
  • 5Dhillon I S,Modha D S.Concept decompositions for large sparse text data using clustering.Machine Learning,2001,42:143-175.
  • 6Strehl A,Ghosh J.Cluster ensembles:a knowledge reuse framework for combining partitionings.Journal of Machine Learning Research,2002,3:583-617.
  • 7Scott D W,Thompson J R.Probability density estimation in higher dimensions.In:Proceedings of the 15th Symposium on the Interface,Amsterdam,Holland,1983.173-179.
  • 8Duda R,Hart P,Stork D.Pattern Classification.Second Edition.New York,USA:John Wiley & Sons,2001.517-599.
  • 9Karypis G,Han E H,Kumar V.CHAMELEON:A hierarchical clustering algorithm using dynamic modeling.IEEE Computer,1999,2(8):68-75.
  • 10Kuncheva L I,Hadjitodorov S T.Using diversity in cluster ensembles.In:Proceedings of the IEEE International Conference on Systems,Man and Cybernetics,Hague,Netherlands,2004.1214-1219.

共引文献92

同被引文献83

引证文献8

二级引证文献46

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部