第6期 谢娟英，等：聚类有效性评价新指标 ·881· al versus external cluster validation indexes[J].Internation- ternational Conference on Machine Learning,Montreal, al journal of computers and communications,2011,5(1): Canada.2009.New York,USA:ACM,2009:1073-1080 27-34 [22]D'HAESELEER P.How does gene expression clustering [11]ROSALES-MENDEZ H,RAMIREZ-CRUZ Y.CICE- work[J].Nature biotechnology,2005,23(12):1499. BCubed:A new evaluation measure for overlapping clus- [23]QUACKENBUSH J.Computational analysis of microar tering algorithms[C]//Iberoamerican Congress on Pattern ray data[J].Nature reviews genetics,2001,2(6):418-427. Recognition.Berlin:Springer Berlin Heidelberg,2013: [24]CHOU CH,SU MC,LAI E.A new cluster validity meas- 157-164. ure for clusters with different densities[Cl/IASTED Inter [12]SAID AB,HADJIDJ R,FOUFOU S.Cluster validity in- national Conference on Intelligent Systems and Control. dex based on jeffrey divergence[J].Pattern analysis and ap- Calgary,Canada:ACTA Press,2003:276-281 plications,2017,20(1:21-31 [25]谢娟英，周颖.一种新聚类评价指标)，陕西师范大学学 [13]XIONG H,WU J,CHEN J.K-means clustering versus val- 报：自然科学版，2015,43(6：1-8. idation measures:a data-distribution perspective[J].IEEE XIE Juanying,ZHOU Ying.A new criterion for clustering transactions on systems,man,and cybernetics,part b(cy- algorithm[J].Journal of Shaanxi normal university:natural bernetics,2009,392)318-331 science edition,2015,43(6):1-8 [14]POWERS D M W.Evaluation:from precision,recall and [26]KAPP AV,TIBSHIRANI R.Are clusters found in one F-factor to ROC,informedness,markedness and correla- dataset present in another dataset[J].Biostatistics,2007, tion[J].Journal of machine learning technologies,2011,2: 8(1)9-31 2229-3981 [27]DAVIES DL,BOULDIN DW.A cluster separation meas- [15]LARSEN B,AONE C.Fast and effective text mining us- ure[J].IEEE transactions on pattern analysis and machine ing linear-time document clustering[C]//Proceedings of the intelligence,1979(2):224-227. fifth ACM SIGKDD international conference on Know- [28]HASHIMOTO W,NAKAMURA T,MIYAMOTO S. ledge discovery and data mining.New York,USA:ACM, Comparison and evaluation of different cluster validity 1999:16-22. measures including their kernelization[J].Journal of ad- [16]ZU EISSEN,B SS M,WIBBROCK F.On cluster validity vanced computational intelligence and intelligent informat- and the information need of users[Cl//Conference on Arti- ics,2009,13(3):204-209. ficial Intelligence and Applications,Benalmadena,Spain, [29]XIE XL,BENI G.A validity measure for fuzzy 2003.Calgary,Canada:ACTA Press,2003:216-221. clustering[J.IEEE transactions on pattern analysis and [1刀谢娟英.无监督学习方法及其应用[M.北京：电子工业 machine intelligence.1991,13(8):841-847. 出版社，2016. [30]ROUSSEEUW PJ.Silhouettes:a graphical aid to the inter- XIE Juanying,Unsupervised learning methods and applica- pretation and validation of cluster analysis[J].Journal of tions[M].Beijing:Publishing House of Electronics In- computational and applied mathematics,1987,20:53-65. dustry,2016. [3]周世兵，徐振源，唐旭清。一种基于近邻传播算法的最佳 [18]XIE J Y,GAO HC,XIE W X,et al.Robust clustering by 聚类数确定方法[.控制与决策，2011,26(8)：1147- detecting density peaks and assigning points based on 1152. fuzzy weighted K-nearest neighbors[J].Information sci- ZHOU Shibing,XU Zhenyuan,TANG Xuqing.Method for ences.2016.354:19-40. determining optimal number of clusters based on affinity [19]谢娟英，高红超，谢维信.K近邻优化的密度峰值快速搜 propagation clustering[J]Control and decision,2011,26(8):1147- 索聚类算法[J,中国科学：信息科学，2016,46(2)： 1152. 258-280. [32]盛骤，谢式千.概率论与数理统计及其应用M.北京：高 XIE Juanying,GAO Hongchao,XIE Weixin.K-nearest 等教育出版社，2004. neighbors optimized clustering algorithm by fast search SHENG Zhou,XIE Shiqian.Probability and mathematical and finding the density peaks of a dataset[J].Scientia sin- statistics and its application[M].Beijing:Higher education ica informationis,2016,46(2):258-280. press,2004. [20]AMIGO E,GONZALO J,ARTILES J,et al.A comparis- [33]LICHMAN M,UCI Machine learning repository [EB/OL]. on of extrinsic clustering evaluation metrics based on form- 2013,University of California,Irvine,School of Informa- al constraints[J].Information retrieval,2009,12(4): tion and Computer Sciences.http://archive.ics.uci.edu/ml. 461-486. [34们谢娟英，高瑞.方差优化初始中心的K-medoids聚类算 [21]VINH NX,EPPS J,BAILEY J.Information theoretic 法[円.计算机科学与探索，2015,9(8：973-984. measures for clusterings comparison:is a correction for XIE Juanying,GAO Rui.K-medoids clustering algorithms chance necessary [C]//Proceedings of the 26th Annual In- with optimized initial seeds by variance[J].Journal of fron-al versus external cluster validation indexes[J]. Internation￾al journal of computers and communications, 2011, 5(1): 27–34. ROSALES-MENDÉZ H, RAMÍREZ-CRUZ Y. CICE￾BCubed: A new evaluation measure for overlapping clus￾tering algorithms[C]//Iberoamerican Congress on Pattern Recognition. Berlin: Springer Berlin Heidelberg, 2013: 157-164. [11] SAID AB, HADJIDJ R, FOUFOU S. Cluster validity in￾dex based on jeffrey divergence[J]. Pattern analysis and ap￾plications, 2017, 20(1): 21–31. [12] XIONG H, WU J, CHEN J. K-means clustering versus val￾idation measures: a data-distribution perspective[J]. IEEE transactions on systems, man, and cybernetics, part b (cy￾bernetics), 2009, 39(2): 318–331. [13] POWERS D M W. Evaluation: from precision, recall and F-factor to ROC, informedness, markedness and correla￾tion[J]. Journal of machine learning technologies, 2011, 2: 2229–3981. [14] LARSEN B, AONE C. Fast and effective text mining us￾ing linear-time document clustering[C]//Proceedings of the fifth ACM SIGKDD international conference on Know￾ledge discovery and data mining. New York, USA: ACM, 1999: 16-22. [15] ZU EISSEN, B S S M, WIßBROCK F. On cluster validity and the information need of users[C]//Conference on Arti￾ficial Intelligence and Applications, Benalmádena, Spain, 2003. Calgary, Canada: ACTA Press, 2003: 216-221. [16] 谢娟英. 无监督学习方法及其应用[M]. 北京: 电子工业 出版社, 2016. XIE Juanying, Unsupervised learning methods and applica￾tions[M]. Beijing: Publishing House of Electronics In￾dustry, 2016. [17] XIE J Y, GAO H C, XIE W X, et al. Robust clustering by detecting density peaks and assigning points based on fuzzy weighted K-nearest neighbors[J]. Information sci￾ences, 2016, 354: 19–40. [18] 谢娟英, 高红超, 谢维信. K 近邻优化的密度峰值快速搜 索聚类算法[J]. 中国科学: 信息科学, 2016, 46(2): 258–280. XIE Juanying, GAO Hongchao, XIE Weixin. K-nearest neighbors optimized clustering algorithm by fast search and finding the density peaks of a dataset[J]. Scientia sin￾ica informationis, 2016, 46(2): 258–280. [19] AMIGÓ E, GONZALO J, ARTILES J, et al. A comparis￾on of extrinsic clustering evaluation metrics based on form￾al constraints[J]. Information retrieval, 2009, 12(4): 461–486. [20] VINH NX, EPPS J, BAILEY J. Information theoretic measures for clusterings comparison: is a correction for chance necessary [C]//Proceedings of the 26th Annual In- [21] ternational Conference on Machine Learning, Montreal, Canada, 2009. New York, USA: ACM, 2009: 1073-1080. D'HAESELEER P. How does gene expression clustering work[J]. Nature biotechnology, 2005, 23(12): 1499. [22] QUACKENBUSH J. Computational analysis of microar￾ray data[J]. Nature reviews genetics, 2001, 2(6): 418–427. [23] CHOU CH, SU MC, LAI E. A new cluster validity meas￾ure for clusters with different densities[C]//IASTED Inter￾national Conference on Intelligent Systems and Control. Calgary, Canada: ACTA Press, 2003: 276-281. [24] 谢娟英, 周颖. 一种新聚类评价指标[J]. 陕西师范大学学 报: 自然科学版, 2015, 43(6): 1–8. XIE Juanying, ZHOU Ying. A new criterion for clustering algorithm[J]. Journal of Shaanxi normal university: natural science edition, 2015, 43(6): 1–8. [25] KAPP AV, TIBSHIRANI R. Are clusters found in one dataset present in another dataset[J]. Biostatistics, 2007, 8(1): 9–31. [26] DAVIES DL, BOULDIN DW. A cluster separation meas￾ure[J]. IEEE transactions on pattern analysis and machine intelligence, 1979(2): 224–227. [27] HASHIMOTO W, NAKAMURA T, MIYAMOTO S. Comparison and evaluation of different cluster validity measures including their kernelization[J]. Journal of ad￾vanced computational intelligence and intelligent informat￾ics, 2009, 13(3): 204–209. [28] XIE XL, BENI G. A validity measure for fuzzy clustering[J]. IEEE transactions on pattern analysis and machine intelligence, 1991, 13(8): 841–847. [29] ROUSSEEUW PJ. Silhouettes: a graphical aid to the inter￾pretation and validation of cluster analysis[J]. Journal of computational and applied mathematics, 1987, 20: 53–65. [30] 周世兵, 徐振源, 唐旭清. 一种基于近邻传播算法的最佳 聚类数确定方法[J]. 控制与决策, 2011, 26(8): 1147– 1152. ZHOU Shibing, XU Zhenyuan, TANG Xuqing. Method for determining optimal number of clusters based on affinity propagation clustering[J]. Control and decision, 2011, 26(8): 1147– 1152. [31] 盛骤, 谢式千. 概率论与数理统计及其应用[M]. 北京: 高 等教育出版社, 2004. SHENG Zhou, XIE Shiqian. Probability and mathematical statistics and its application[M]. Beijing: Higher education press, 2004. [32] LICHMAN M, UCI Machine learning repository[EB/OL]. 2013, University of California, Irvine, School of Informa￾tion and Computer Sciences. http://archive.ics.uci.edu/ml. [33] 谢娟英, 高瑞. 方差优化初始中心的 K-medoids 聚类算 法[J]. 计算机科学与探索, 2015, 9(8): 973–984. XIE Juanying, GAO Rui. K-medoids clustering algorithms with optimized initial seeds by variance[J]. Journal of fron- [34] 第 6 期 谢娟英，等：聚类有效性评价新指标 ·881·