全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

球极平面逆投影迭代谱聚类算法

DOI: 10.13195/j.kzyjc.2012.1783, PP. 396-402

Keywords: 球极平面逆投影,谱聚类,偏振定理,模式识别

Full-Text   Cite this paper   Add to My Lib

Abstract:

提出一种相似矩阵迭代修正并聚类算法,分为偏振定理的谱分离数据和球极平面逆投影的几何分离数据两步.首先将数据谱分解,得到低维距离矩阵;然后投影到双随机矩阵,隐式进行一次球极平面逆投影,几何对称分离数据;最后解算投影后坐标,得到新相似矩阵.实验在人工合成数据和自然数据上进行,结果表明所提出算法修正了数据的相似度,并获得了正确的聚类个数,对尺度参数变化有较强的鲁棒性,聚类性能比修正前有较大提升.

References

[1]  徐森, 卢志茂, 顾国昌. 使用谱聚类算法解决文本聚类集成问题[J]. 通信学报, 2010, 131(6): 58-66.
[2]  (Xu S, Lu Z M, Gu G C. Spectral clustering algorithms for document cluster ensemble problem[J]. J on Communications, 2010, 131(6): 58-66.)
[3]  Dhillon I S, Guan Y, Kulis B. Kernel ??-means: Spectral clustering and normalized cuts[C]. Proc of the 10th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining. New York: ACM Press, 2004: 551-556.
[4]  Alzate C, Suykens J A K. Multiway spectral clustering with out-of-sample extensions through weighted kernel PCA[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2010, 32(2): 335-347.
[5]  Xiang T, Gong S. Spectral clustering with eigenvector selection[J]. Pattern Recognition, 2008, 41(3): 1012-1029.
[6]  Zhao F, Jiao L, Liu H, et al. Spectral clustering with eigenvector selection based on entropy ranking[J]. Neurocomputing, 2010, 73(10): 1704-1717.
[7]  Rebagliati N, Verri A. Spectral clustering with more than?K eigenvectors[J]. Neurocomputing, 2011, 74(9): 1391-1401.
[8]  Lin F, Cohen W W. Power iteration clustering[C]. Proc of the 27th Int Conf on Machine Learning. Haifa: IMLS, 2010: 655-662.
[9]  Brand M, Huang K. A unifying theorem for spectral embedding and clustering[C]. Proc of the 9th IntWorkshop on Artificial Intelligence and Statistics. Key West: SAIS, 2003.
[10]  Perona P, Zelnik-Manor L. Self-tuning spectral clustering[C]. Advances in Neural Information Processing Systems. Vancouver: MIT Press, 2004: 1601-1608.
[11]  张学工. 模式识别[M]. 北京: 清华大学出版社, 2010: 173-176.
[12]  (Zhang X G. Pattern recognition[M]. Beijing: Tsinghua University Press, 2010: 173-176.)
[13]  Von Luxburg U. A tutorial on spectral clustering[J]. Statistics and Computing, 2007, 17(4): 395-416.
[14]  Sinkhorn R. A relationship between arbitrary positive matrices and doubly stochastic matrices[J]. The Annals of Mathematical Statistics, 1964, 35(2): 876-879.
[15]  Johnson C R, Masson R D, Trosset M W. On the diagonal scaling of Euclidean distance matrices to doubly stochastic matrices[J]. Linear Algebra and Its Applications, 2005, 397(1): 253-264.
[16]  贾春霞. 凸约束的非线性方程系统的仿射内点信赖域法[D]. 上海: 上海师范大学数理信息学院, 2008.
[17]  (Jia C X. Affine scaling interior trust region methods for solving convex constrained nonlinear systems[D]. Shanghai: Mathematics and Science College, Shanghai Normal University, 2008.)
[18]  UCI data set. Iris, wine data set[DB/OL]. (1988-7-1)[2011-11-28]. http://archive.ics.uci.edu/ml/datasets.html.
[19]  高翠芳. 模糊聚类新算法及应用研究[D]. 无锡: 江南大学数字媒体学院, 2011.
[20]  (Gao C F. Novel fuzzy clustering algorithms and applications[D]. Wuxi: School of Digital Media, Jiangnan University, 2011.)
[21]  Ng A Y, Jordan M I, Weiss Y. On spectral clustering: Analysis and an algorithm[C]. Advances in Neural Information Processing Systems. Vancouver: MIT Press, 2001: 849-856.
[22]  Shi J, Malik J. Normalized cuts and image segmentation[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000, 22(8): 888-905.
[23]  姜园, 张朝阳, 仇佩亮, 等. 用于数据挖掘的聚类算法[J]. 电子与信息学报, 2005, 27(4): 655-662.
[24]  (Jiang Y, Zhang Z Y, Qiu P L, et al. Clustering algorithms used in data mining[J]. J of Electronics and Information Technology, 2005, 27(4): 655-662.)

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133