自适应谱聚类算法研究

被引:15
作者
卜德云
张道强
机构
[1] 南京航空航天大学计算机科学与工程系
关键词
自适应; 谱聚类; 参数选取;
D O I
暂无
中图分类号
TP301.6 [算法理论];
学科分类号
081202 ;
摘要
谱聚类能识别出在原空间中线性不可分的聚类,且其效果优于传统聚类算法.谱聚类要想获得好的效果必须选择一个合适的尺度参数,本文在传统谱聚类算法的基础上引入类似核选取的技巧,提出了一个能自动选取该尺度参数的自适应谱聚类算法.将该算法和现有的谱聚类参数选择算法作了比较,在人工数据集和UCI数据集上的实验表明,自适应谱聚类算法在很多情况下优于其它参数选择算法.
引用
收藏
页码:22 / 26
页数:5
相关论文
共 14 条
[1]  
Onspectral clustering:analys-is and an algorithm. NGA,JORDANM,WEISS Y. Advancesin Neural Information Pro-cessing Systems(NIPS) . 2002
[2]   A tutorial on spectral clustering [J].
von Luxburg, Ulrike .
STATISTICS AND COMPUTING, 2007, 17 (04) :395-416
[3]  
Atutorial on spectral clustering. LUXBURGvon U. Statistics and Computing . 2007
[4]  
On clusterings-good,bad and spectral. Kannan R,Vempala S,Vetta A. Proceedings of the Annual IEEESymposium on Foundations of Computer Science . 2000
[5]  
Pattern Recognition with Fuzzy Objective Function Algorithms. JC Bezdek. . 1981
[6]  
Data clustering:a review. A.K.Jain,,M.N.Murty,,P.J.Flynn. ACM conputing surveys . 1999
[7]  
Normalized cuts and image segmentation. Shi J,Malik J. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2000
[8]  
Algebraic connectivity of graphs. Fiedler M. Czechoslovak Mathematical Journal . 1973
[9]  
UCI repository of machine learning databases. BLAKE C,KEOGHE,MERZ CJ. http://www.ics.uci.edu/~mlearn/MLRepository.html . 2009
[10]  
Adaptive kernel principal component analysis with unsupervised learning of kernels. ZHANG D,ZHOUZ H,CHENS. Proceedings of the6th IEEEInternational Conference on Data Mining(ICDM’06) . 2006