Resampling-based selective clustering ensembles
Resampling-based selective clustering ensembles
复制标题
DOI：
10.1016/j.patrec.2008.10.007
复制
发表时间：
2009-02-01
影响因子：
5.1
通讯作者：
Ren, Qjngsheng
中科院分区：
文献类型：
--
作者：
Hong, Yi;Kwong, Sam;Ren, Qjngsheng
传统的聚类集成方法结合了所有获得的现有聚类结果。然而，我们观察到，如果仅组合所有可用聚类结果的一部分，通常可以获得更好的聚类解决方案。本文提出了一种新颖的聚类集成方法，称为基于重采样的选择性聚类集成方法。所提出的选择性聚类集成方法的工作原理是通过重采样技术评估所有获得的聚类结果的质量，并选择性地选择部分有希望的聚类结果来构建集成委员会。通过结合集成委员会的聚类结果得到最终的解决方案。在多个真实数据集上的实验结果表明，与传统的聚类集成方法相比，基于重采样的选择性聚类集成方法通常能够获得更好的解决方案。 (C) 2008 Elsevier B.V. 保留所有权利。
Traditional clustering ensembles methods combine all obtained clustering results at hand. However, we observe that it can often achieve a better clustering solution if only part of all available clustering results are combined. This paper proposes a novel clustering ensembles method, termed as resampling-based selective clustering ensembles method. The proposed selective clustering ensembles method works by evaluating the qualities of all obtained clustering results through resampling technique and selectively choosing part of promising clustering results to build the ensemble committee. The final solution is obtained through combining the clustering results of the ensemble committee. Experimental results on several real data sets demonstrate that resampling-based selective clustering ensembles method is often able to achieve a better solution when compared with traditional clustering ensembles methods. (C) 2008 Elsevier B.V. All rights reserved.