Paper Info
Title
Cluster ensemble framework based on the group method of data handling.
Abstract
Graphical abstractCE-GMDH contains the following three components: (1) initial solutions, (2) a transfer function (mechanism for the mutation of this organisation), and (3) an external criterion (selection mechanism). Three CE-GMDH models were proposed in our study according to different transfer functions. Display Omitted HighlightsA cluster ensemble framework based on the group method of data handling was proposed.The components of the CE-GMDH can be chosen according to the target of the application.Three novel transfer functions in CE-GMDH were proposed.CE-GMDH outperforms the other cluster ensemble algorithms and frameworks. 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.
Year
DOI
Venue
2016
10.1016/j.asoc.2016.01.043
Appl. Soft Comput.
Keywords
Field
DocType
Cluster ensemble,GMDH,Evolutionary algorithm,Least squares,CSPA,Semidefinite programming
Least squares,Data mining,Evolutionary algorithm,Computer science,Robustness (computer science),Transfer function,Artificial intelligence,Group method of data handling,Ensemble learning,Semidefinite programming,Machine learning
Journal
Volume
Issue
ISSN
43
C
1568-4946
Citations 
PageRank 
References 
4
0.40
25
Authors
6
Name
Order
Citations
PageRank
Ge-Er Teng1212.32
Changzheng He21529.31
Jin Xiao3808.89
Yue He410516.62
Bing Zhu5404.03
Xiaoyi Jiang62184206.38