正在加载图片...
·458 智能系统学报 第12卷 [11]曾令伟,伍振兴,杜文才.基于改进自监督学习群体智能 4 结束语 (ILC的高性能聚类算法[J].重庆邮电大学学报:自 在聚类的实际应用中,大多数数据集都含有一 然科学版,2016,28(1):131-137. 定量的辅助信息,这些辅助信息中含有重要的数据 ZENG Lingwei,WU Zhenxing,DU Wencai.Improved self 特征,但是这些辅助信息在聚类过程中常常被忽 supervised learning collection intelligence based high performance data clustering approach [J].Journal of 略。本文提出了一种利用数据集的辅助信息进行 Chongqing university of posts and telecommunications: 距离学习的方法,进而提出了一种改进的CM算法 natural science edition,2016,28(1):131-137. HR-FCM。用数据集的辅助信息进行距离学习得到 [12]程肠,王士同.基于局部保留投影的多可选聚类发掘算 的混合函数,不仅能够反映出数据集本身的特征, 法[J]智能系统学报,2016,11(5):600-607. 而且比欧式距离更加契合数据集,更加适合于实际 CHENG Yang,WANG Shitong.A multiple alternative 应用。在含有辅助信息的数据集中,本文提出的 clusterings mining algorithm using locality preserving HR-FCM算法具有较好的聚类性能和鲁棒性。实验 projections[].CAAI transactions on intelligent systems, 结果证明了结论。 2016,11(5):600-607. [13 DUDA R O,HART P E,STORK D G.Pattern 参考文献: classification[M]//Pattern classification.Wiley,2001: 119-131. [1]王骏,王士同.基于混合距离学习的双指数模糊C均值 [14]MEI J P,CHEN L.Fuzzy clustering with weighted medoids 算法[J].软件学报,2010,21(8):1878-1888. for relational data[].Pattern recognition,2010,43(5): WANG Jun,WANG Shitong.Double indices FCM algorithm 1964-1974. based on hybrid distance metric learning[J].Journal of [15]HOPPNER F,KLAWONN F.Improved fuzzy partitions for software,.2010,21(8):1878-1888. fuzzy regression models J].International journal of [2]WU L,HOI S C H,JIN R,et al.Learning bregman approximate reasoning,2003,32(2/3):85-102. distance functions for semi-supervised clustering[J].IEEE [16]ZHU L,CHUNG F L,WANG S.Generalized fuzzy C-means transactions on knowledge and data engineering,2012,24 clustering algorithm with improved fuzzy partitions[.IEEE (3):478-491. transactions on systems man and cybernetics part B,2009,39 [3 WU K L,YANG M S.Alternative c-means clustering (3):578-591. algorithms J ]Pattern recognition,2002.35(10): [17]STREHL A,GHOSH J.Cluster ensembles-a knowledge reuse 2267-2278. framework for combining multiple partitions[].Journal of [4]XING E P,NG A Y,JORDAN M I,et al.Distance metric machine leaming research,2002,3(3):583-617. learning,with application to clustering with side- [18]IWAYAMA M,TOKUNAGA T.Hierarchical Bayesian information[J].Advances in neural information processing clustering for automatic text classification J].IJCAI, 8 ystems,2003,15:505-512. 1996:1322-1327. [5]BAR-Hillel A,HERTZ T,SHENTAL N,et al.Learning a [19]RAND W M.Objective criteria for the evaluation of mahalanobis metric from equivalence constraints[].Joumal clustering methods[J].Journal of the american statistical of machine learning research,2005,6(6):937-965. association,1971,66(336):846-850. [6]郭瑛洁,王士同,许小龙.基于最大间隔理论的组合距 作者简介: 离学习算法[J].智能系统学报,2015,10(6): 卞则康,男,1993年生,硕士研究 843-850. 生,主要研究方向为人工智能和模式 [7]YE J,ZHAO Z,LIU H.Adaptive distance metric learning 识别。 for clustering[C]//IEEE Conference on Computer Vision and Pattern Recognition.Minneapolis,USA,2007:1-7. [8]WANG X,WANG Y,WANG L.Improving fuzzy c-means clustering based on feature-weight learning [J].Pattern recognition letters,2004,25(10):1123-1132. 王土同,男,1964年生,教授,博士生 [9]HE P,XU X,HU K,et al.Semi-supervised clustering via 导师,主要研究方向为人工智能与模式识 multi-level random walk[J].Pattern recognition,2014,47 别。发表学术论文近百篇,其中被SCI,E (2):820-832. 检索50余篇。 [10]HOI S C H,LIU W,LYU M R,et al.Learning distance metrics with contextual constraints for image retrieval [C]//IEEE Conference on Computer Vision and Pattern Recognition.New York,USA,2006:2072-2078.4 结束语 在聚类的实际应用中,大多数数据集都含有一 定量的辅助信息,这些辅助信息中含有重要的数据 特征,但是这些辅助信息在聚类过程中常常被忽 略。 本文提出了一种利用数据集的辅助信息进行 距离学习的方法,进而提出了一种改进的 FCM 算法 HR⁃FCM。 用数据集的辅助信息进行距离学习得到 的混合函数,不仅能够反映出数据集本身的特征, 而且比欧式距离更加契合数据集,更加适合于实际 应用。 在含有辅助信息的数据集中,本文提出的 HR⁃FCM 算法具有较好的聚类性能和鲁棒性。 实验 结果证明了结论。 参考文献: [1]王骏, 王士同. 基于混合距离学习的双指数模糊 C 均值 算法[J]. 软件学报, 2010, 21(8): 1878-1888. WANG Jun, WANG Shitong. Double indices FCM algorithm based on hybrid distance metric learning [ J ]. Journal of software, 2010, 21(8): 1878-1888. [2] WU L, HOI S C H, JIN R, et al. Learning bregman distance functions for semi⁃supervised clustering[ J]. IEEE transactions on knowledge and data engineering, 2012, 24 (3): 478-491. [ 3 ] WU K L, YANG M S. Alternative c⁃means clustering algorithms [ J ]. Pattern recognition, 2002, 35 ( 10 ): 2267-2278. [4]XING E P, NG A Y, JORDAN M I, et al. Distance metric learning, with application to clustering with side⁃ information[ J]. Advances in neural information processing systems, 2003, 15: 505-512. [5] BAR⁃Hillel A, HERTZ T, SHENTAL N, et al. Learning a mahalanobis metric from equivalence constraints[J]. Journal of machine learning research, 2005, 6(6): 937-965. [6]郭瑛洁, 王士同, 许小龙. 基于最大间隔理论的组合距 离学 习 算 法 [ J ]. 智 能 系 统 学 报, 2015, 10 ( 6 ): 843-850. [7]YE J, ZHAO Z, LIU H. Adaptive distance metric learning for clustering[ C] / / IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, USA, 2007: 1-7. [8] WANG X, WANG Y, WANG L. Improving fuzzy c⁃means clustering based on feature⁃weight learning [ J ]. Pattern recognition letters, 2004, 25(10): 1123-1132. [9]HE P, XU X, HU K, et al. Semi⁃supervised clustering via multi⁃level random walk[J]. Pattern recognition, 2014, 47 (2): 820-832. [10]HOI S C H, LIU W, LYU M R, et al. Learning distance metrics with contextual constraints for image retrieval [C] / / IEEE Conference on Computer Vision and Pattern Recognition. New York, USA, 2006: 2072-2078. [11]曾令伟,伍振兴,杜文才.基于改进自监督学习群体智能 (ISLCI)的高性能聚类算法[J].重庆邮电大学学报: 自 然科学版, 2016, 28(1): 131-137. ZENG Lingwei, WU Zhenxing, DU Wencai. Improved self supervised learning collection intelligence based high performance data clustering approach [ J ]. Journal of Chongqing university of posts and telecommunications: natural science edition,2016, 28(1): 131-137. [12]程旸,王士同. 基于局部保留投影的多可选聚类发掘算 法[J].智能系统学报, 2016, 11(5): 600-607. CHENG Yang, WANG Shitong. A multiple alternative clusterings mining algorithm using locality preserving projections[ J]. CAAI transactions on intelligent systems, 2016, 11(5): 600-607. [ 13 ] DUDA R O, HART P E, STORK D G. Pattern classification[M] / / Pattern classification. Wiley, 2001: 119-131. [14]MEI J P, CHEN L. Fuzzy clustering with weighted medoids for relational data[J]. Pattern recognition, 2010, 43(5): 1964-1974. [15]HOPPNER F, KLAWONN F. Improved fuzzy partitions for fuzzy regression models [ J ]. International journal of approximate reasoning, 2003, 32(2 / 3): 85-102. [16]ZHU L, CHUNG F L, WANG S. Generalized fuzzy C⁃means clustering algorithm with improved fuzzy partitions[J]. IEEE transactions on systems man and cybernetics part B, 2009, 39 (3): 578-591. [17]STREHL A, GHOSH J. Cluster ensembles⁃a knowledge reuse framework for combining multiple partitions [ J]. Journal of machine learning research, 2002, 3(3): 583-617. [18 ] IWAYAMA M, TOKUNAGA T. Hierarchical Bayesian clustering for automatic text classification [ J ]. IJCAI, 1996: 1322-1327. [19 ] RAND W M. Objective criteria for the evaluation of clustering methods[ J]. Journal of the american statistical association, 1971, 66(336): 846-850. 作者简介: 卞则康,男,1993 年生,硕士研究 生,主要研究方向为人工智能和模式 识别。 王士同,男,1964 年生,教授,博士生 导师,主要研究方向为人工智能与模式识 别。 发表学术论文近百篇,其中被 SCI、EI 检索 50 余篇。 ·458· 智 能 系 统 学 报 第 12 卷
<<向上翻页
©2008-现在 cucdc.com 高等教育资讯网 版权所有