可变相似性度量的近邻传播聚类

董俊; 王锁萍; 熊范纶

doi:10.3724/SP.J.1146.2009.01066

可变相似性度量的近邻传播聚类

doi: 10.3724/SP.J.1146.2009.01066

计量
- 文章访问数: 5028
- HTML全文浏览量: 212
- PDF下载量: 3907
- 被引次数: 0
出版历程
- 收稿日期: 2009-08-05
- 修回日期: 2010-01-13
- 刊出日期: 2010-03-19

Affinity Propagation Clustering Based on Variable-Similarity Measure

摘要

摘要: 近邻传播(AP)聚类算法面临的一个问题是不适用于多重尺度及任意空间形状的数据聚类处理。该文从数据分布特性的表征出发，提出了一种改进的近邻传播聚类算法AP-VSM (Affinity Propagation based on Variable-Similarity Measure)。首先，综合数据的全局与局部分布特性，设计了一种数据可变相似性度量计算方法，该度量可以有效地反映数据实际聚类的分布特性；然后在传统AP算法框架基础上，构造出基于可变相似性度量的近邻传播聚类算法，从而拓展了传统AP算法的数据处理能力。仿真实验验证了新方法性能优于传统AP算法。
- 数据处理; 聚类分析; 近邻传播聚类; 可变相似性度b量; 流形分析
Abstract: Affinity Propagation (AP) clustering is not fit to deal with multi-scale data cluster as well as the arbitrary shape cluster issue. Therefore, an improved affinity propagation clustering algorithm AP-VSM (Affinity Propagation based on Variable-Similarity Measure) is proposed embarking from the token of data distribution characters. First, a kind of variable-similarity measure method is devised according of characters of global and local data distribution, which has the ability of describing the characters of data clustering effectively. Then AP-VSM clustering algorithm is proposed base on the frame of traditional AP algorithm, and this method has extended data processing capacity compared with traditional AP. The simulation results show that the new method is outperforming traditional AP algorithm.

HTML全文

参考文献(1)

Frey B J and Dueck D. Clustering by passing messagesbetween data points[J].Science.2007, 315(5814):972-976[2]Givoni I E and Frey B J. A binary variable model for affinitypropagation[J].Neural Computation.2009, 21(6):1589-1600[3]Jia Sen, Qian Yun-tao, and Ji Zhen. Band selection forhyperspectral imagery using affinity. Propagation.Proceedings of the 2008 Digital Image Computing:Techniques and Applications, Canberra, ACT, 1-3.12.2008:137-141.[4]Gang Li, Lei Guo, and Liu Tian-ming, et al.. Grouping ofbrain MR images via affinity propagation. IEEEInternational Symposium on Circuits and Systems, 2009(ISCAS 2009) Taipei, Taiwan, 5.24. 2009: 2425-2428.[5]Dueck D, Frey B J, and Jojic N, et al.. Constructingtreatment portfolios using affinity propagation[C].Proceedings of 12th Annual International Conference,RECOMB 2008. Singapore. 3.30-4.2, 2008: 360-371.[6]Leone M, Sumedha, and Weigt M. Clustering bysoft-constraint affinity propagation: applications to geneexpressiondata[J].Bioinformatics.2007, 23(20):2708-2715[7]王开军, 张军英, 李丹等. 自适应仿射传播聚类. 自动化学报,2007, 33(12): 1242-1246.Wang Kai-jun, Zhang Jun-ying, and Li Dan. Adaptiveaffinity propagation clustering. Acta Automatica Sinica,2007, 33(12): 1242-1246.[8]王玲, 薄列峰, 焦李成. 密度敏感的半监督谱聚类. 软件学报,2007, 18(10): 2412-2422.Wang L, Bo L F, and Jiao L C. Density-Sensitivesemi-supervised spectral clustering. Journal of Software, 2007,18(10): 2412-2422.[9]Alexander Hinneburg and Daniel A Keim. A generalapproach to clustering in large databases with noise[J].Knowledge and Information Systems.2003, 5(4):387-415[10]Little M A, McSharry P E, Hunter E J, and Lorraine O.Suitability of dysphonia measurements for telemonitoring ofParkinson's disease. IEEE Transactions on BiomedicalEngineering, 2009, 56(4): 1015-1022.

施引文献

资源附件(0)

访问统计