Cluster ensemble framework based on the group method of data handling
Cluster ensemble framework based on the group method of data handling
复制标题
基于分组数据处理方法的集群集成框架
DOI：
10.1016/j.asoc.2016.01.043
复制
发表时间：
2016-06
影响因子：
8.7
通讯作者：
Jiang Xiaoyi
中科院分区：
文献类型：
--
作者：
Teng Geer;He Changzheng;Xiao Jin;He Yue;Zhu Bing;Jiang Xiaoyi
聚类集成是提高无监督分类方案鲁棒性和稳定性的一种有效方法。将分组数据处理方法（GMDH）引入到集群集成中，提出了一种新的集群集成框架，称为基于分组数据处理方法（CE-GMDH）的集群集成框架。CE-GMDH由初始解、传递函数和外部判据三部分组成。根据不同类型的传递函数和外部准则，可以建立多个CE-GMDH模型。本文提出了基于不同传递函数的三种新模型：最小二乘法、基于聚类的相似性划分算法和半定规划。在合成数据集和真实数据集上，比较了CE-GMDH在不同传递函数下的性能，以及一些最先进的聚类集成算法和聚类集成框架的性能。实验结果表明，CE-GMDH通过其独特的建模过程可以提高作为传递函数的聚类集成算法的性能。这也表明CE-GMDH比其他聚类集成算法和聚类集成框架取得了更好或相当的结果。
Cluster ensemble is a powerful method for improving both the robustness and the stability of unsupervised classification solutions. This paper introduced group method of data handling (GMDH) to cluster ensemble, and proposed a new cluster ensemble framework, which named cluster ensemble framework based on the group method of data handling (CE-GMDH). CE-GMDH consists of three components: an initial solution, a transfer function and an external criterion. Several CE-GMDH models can be built according to different types of transfer functions and external criteria. In this study, three novel models were proposed based on different transfer functions: least squares approach, cluster-based similarity partitioning algorithm and semidefinite programming. The performance of CE-GMDH was compared among different transfer functions, and with some state-of-the-art cluster ensemble algorithms and cluster ensemble frameworks on synthetic and real datasets. Experimental results demonstrate that CE-GMDH can improve the performance of cluster ensemble algorithms which used as the transfer functions through its unique modelling process. It also indicates that CE-GMDH achieves a better or comparable result than the other cluster ensemble algorithms and cluster ensemble frameworks.
登录
查看更多内容
影响因子：
3
作者：
Jen-Chieh Liu;Darren J. Martin;R. Moon;J. Youngblood
通讯作者：
Jen-Chieh Liu;Darren J. Martin;R. Moon;J. Youngblood
DOI：
10.1016/j.eswa.2010.11.007
发表时间：
2011-05
期刊：
Expert Syst. Appl.
影响因子：
--
作者：
S. Liao;Yin-ju Chen;Hsin-hua Hsieh
通讯作者：
S. Liao;Yin-ju Chen;Hsin-hua Hsieh
影响因子：
10.2
作者：
d'Aspremont, Alexandre;El Ghaoui, Laurent;Lanckriet, Gert R. G.
通讯作者：
Lanckriet, Gert R. G.
DOI：
10.1137/1.9781611972740.35
发表时间：
2004
期刊：
--
影响因子：
--
作者：
A. Topchy;Anil K. Jain;W. Punch
通讯作者：
A. Topchy;Anil K. Jain;W. Punch
DOI：
10.1109/tsmcc.2012.2222025
发表时间：
2012-11
期刊：
IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)
影响因子：
--
作者：
Weiwei Zhuang;Yanfang Ye;Yong Chen;Tao Li
通讯作者：
Weiwei Zhuang;Yanfang Ye;Yong Chen;Tao Li