计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (19): 15-17.

• 博士论坛 • 上一篇    下一篇

聚类有效性的组合评价方法

刘燕驰1,高学东1,国宏伟2,武 森1   

  1. 1.北京科技大学 经济管理学院,北京 100083
    2.北京科技大学 冶金与生态工程学院,北京 100083
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-07-01 发布日期:2011-07-01

Ensembling clustering validation indices

LIU Yanchi1,GAO Xuedong1,GUO Hongwei2,WU Sen1   

  1. 1.School of Economics and Management,University of Science and Technology Beijing,Beijing 100083,China
    2.School of Metallurgical and Ecological Engineering,University of Science and Technology Beijing,Beijing 100083,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-07-01 Published:2011-07-01

摘要: 针对现有研究中给出的聚类有效性指标不能有效评价不同结构数据集的聚类结果问题,提出一种使用多个有效性指标进行聚类评价的组合方法。引入D-S(Dempster-Shafer)证据理论对多个有效性指标结果进行集成,并得到最终的聚类评价结果。仿真实验和分析验证了该方法的可行性与有效性。

关键词: 聚类评价, D-S证据理论, 有效性指标, 聚类数

Abstract: Clustering validation is a key factor to the success of clustering.One of the approaches to validate the clustering results is clustering validation index.However,there is no general index for all kinds of data structures.A Dempster-Shafer,(D-S) evidence theory based ensemble method for multiple indices is proposed recently,named D-S theory based Validation method(DSV).Experimental results and analysis on various synthetic data sets show that DSV outperforms single clustering validation index.

Key words: clustering validation, Dempster-Shafer(D-S) evidence theory, clustering validation index, cluster number