Hybrid sampling on mutual information entropy-based clustering ensembles for optimizations

Feng Yeh Wang; Cheng Yang; Zhiyi Lin; Yuanxiang Li; Yuan Yuan

doi:10.1016/j.neucom.2009.11.011

Hybrid sampling on mutual information entropy-based clustering ensembles for optimizations

Feng Yeh Wang, Cheng Yang, Zhiyi Lin, Yuanxiang Li, Yuan Yuan

Computer Science Research Group

Research output: Contribution to journal › Article › peer-review

Abstract

In this paper, we focus on the design of bivariate EDAs for discrete optimization problems and propose a new approach named HSMIEC. While the current EDAs require much time in the statistical learning process as the relationships among the variables are too complicated, we employ the Selfish gene theory (SG) in this approach, as well as a Mutual Information and Entropy based Cluster (MIEC) model is also set to optimize the probability distribution of the virtual population. This model uses a hybrid sampling method by considering both the clustering accuracy and clustering diversity and an incremental learning and resample scheme is also set to optimize the parameters of the correlations of the variables. Compared with several benchmark problems, our experimental results demonstrate that HSMIEC often performs better than some other EDAs, such as BMDA, COMIT, MIMIC and ECGA.

Original language	English
Pages (from-to)	1457-1464
Number of pages	8
Journal	Neurocomputing
Volume	73
Issue number	7-9
Early online date	16 Dec 2009
DOIs	https://doi.org/10.1016/j.neucom.2009.11.011
Publication status	Published - Mar 2010
Event	17th European Symposium on Artificial Neural Networks: Advances in Computational Intelligence and Learning - Bruges, Belgium Duration: 22 Apr 2009 → 24 Apr 2009

Bibliographical note

17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning, ESANN 2009, 22-24 April 2009
Bruges, Belgium.

Keywords

clustering ensembles
estimation of distribution algorithm
mutual information entropy
selfish gene theory

Access to Document

10.1016/j.neucom.2009.11.011

Cite this

@article{88e6e99212f943ce93c581be564abba0,

title = "Hybrid sampling on mutual information entropy-based clustering ensembles for optimizations",

abstract = "In this paper, we focus on the design of bivariate EDAs for discrete optimization problems and propose a new approach named HSMIEC. While the current EDAs require much time in the statistical learning process as the relationships among the variables are too complicated, we employ the Selfish gene theory (SG) in this approach, as well as a Mutual Information and Entropy based Cluster (MIEC) model is also set to optimize the probability distribution of the virtual population. This model uses a hybrid sampling method by considering both the clustering accuracy and clustering diversity and an incremental learning and resample scheme is also set to optimize the parameters of the correlations of the variables. Compared with several benchmark problems, our experimental results demonstrate that HSMIEC often performs better than some other EDAs, such as BMDA, COMIT, MIMIC and ECGA.",

keywords = "clustering ensembles, estimation of distribution algorithm, mutual information entropy, selfish gene theory",

author = "Wang, {Feng Yeh} and Cheng Yang and Zhiyi Lin and Yuanxiang Li and Yuan Yuan",

note = "17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning, ESANN 2009, 22-24 April 2009 Bruges, Belgium.; 17th European Symposium on Artificial Neural Networks : Advances in Computational Intelligence and Learning, ESANN 2009 ; Conference date: 22-04-2009 Through 24-04-2009",

year = "2010",

month = mar,

doi = "10.1016/j.neucom.2009.11.011",

language = "English",

volume = "73",

pages = "1457--1464",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier",

number = "7-9",

}

TY - JOUR

T1 - Hybrid sampling on mutual information entropy-based clustering ensembles for optimizations

AU - Wang, Feng Yeh

AU - Yang, Cheng

AU - Lin, Zhiyi

AU - Li, Yuanxiang

AU - Yuan, Yuan

N1 - 17th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning, ESANN 2009, 22-24 April 2009 Bruges, Belgium.

PY - 2010/3

Y1 - 2010/3

N2 - In this paper, we focus on the design of bivariate EDAs for discrete optimization problems and propose a new approach named HSMIEC. While the current EDAs require much time in the statistical learning process as the relationships among the variables are too complicated, we employ the Selfish gene theory (SG) in this approach, as well as a Mutual Information and Entropy based Cluster (MIEC) model is also set to optimize the probability distribution of the virtual population. This model uses a hybrid sampling method by considering both the clustering accuracy and clustering diversity and an incremental learning and resample scheme is also set to optimize the parameters of the correlations of the variables. Compared with several benchmark problems, our experimental results demonstrate that HSMIEC often performs better than some other EDAs, such as BMDA, COMIT, MIMIC and ECGA.

AB - In this paper, we focus on the design of bivariate EDAs for discrete optimization problems and propose a new approach named HSMIEC. While the current EDAs require much time in the statistical learning process as the relationships among the variables are too complicated, we employ the Selfish gene theory (SG) in this approach, as well as a Mutual Information and Entropy based Cluster (MIEC) model is also set to optimize the probability distribution of the virtual population. This model uses a hybrid sampling method by considering both the clustering accuracy and clustering diversity and an incremental learning and resample scheme is also set to optimize the parameters of the correlations of the variables. Compared with several benchmark problems, our experimental results demonstrate that HSMIEC often performs better than some other EDAs, such as BMDA, COMIT, MIMIC and ECGA.

KW - clustering ensembles

KW - estimation of distribution algorithm

KW - mutual information entropy

KW - selfish gene theory

UR - http://www.scopus.com/inward/record.url?scp=77649238021&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2009.11.011

DO - 10.1016/j.neucom.2009.11.011

M3 - Article

AN - SCOPUS:77649238021

SN - 0925-2312

VL - 73

SP - 1457

EP - 1464

JO - Neurocomputing

JF - Neurocomputing

IS - 7-9

T2 - 17th European Symposium on Artificial Neural Networks

Y2 - 22 April 2009 through 24 April 2009

ER -

Hybrid sampling on mutual information entropy-based clustering ensembles for optimizations

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

A new variational radial basis function approximation for inference in multivariate diffusions

A variational radial basis function approximation for diffusion processes

Cite this