基于马尔科夫毯约束的最优贝叶斯网络结构学习算法

Xiang Yuan Tan; Xiao Guang Gao; Chu Chao He

doi:10.3969/j.issn.0372-2112.2019.09.012

基于马尔科夫毯约束的最优贝叶斯网络结构学习算法

Translated title of the contribution: Learning Optimal Bayesian Network Structure Constrained with Markov Blanket

Xiang Yuan Tan, Xiao Guang Gao, Chu Chao He

School of Electronics and Information

Northwestern Polytechnical University Xian

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

6 Scopus citations

Abstract

To solve the problem about structure learning of optimal Bayesian network, this paper proposes Dynamic Programming Constrained with Markov Blanket (DPCMB), which uses Markov Blanket calculated by Incremental Association Markov Blanket (IAMB) to reduce the number of scoring calculations in Dynamic Programming. We research on the effect of the significance value in IAMB on the performance indicators of DPCMB algorithm, and give reasonable suggestions for adjusting the significance value. Experimental results show that the DPCMB algorithm can adjust the significance value so that the accuracy of the algorithm is comparable to that of the DP algorithm, and running time, score calculation times, and memory requirements of the algorithm are greatly reduced.

Translated title of the contribution	Learning Optimal Bayesian Network Structure Constrained with Markov Blanket
Original language	Chinese (Traditional)
Pages (from-to)	1898-1904
Number of pages	7
Journal	Tien Tzu Hsueh Pao/Acta Electronica Sinica
Volume	47
Issue number	9
DOIs	https://doi.org/10.3969/j.issn.0372-2112.2019.09.012
State	Published - 1 Sep 2019

Access to Document

10.3969/j.issn.0372-2112.2019.09.012

Cite this

@article{c5a59b92563943cdbd8835ad806cfd8b,

title = "基于马尔科夫毯约束的最优贝叶斯网络结构学习算法",

abstract = "To solve the problem about structure learning of optimal Bayesian network, this paper proposes Dynamic Programming Constrained with Markov Blanket (DPCMB), which uses Markov Blanket calculated by Incremental Association Markov Blanket (IAMB) to reduce the number of scoring calculations in Dynamic Programming. We research on the effect of the significance value in IAMB on the performance indicators of DPCMB algorithm, and give reasonable suggestions for adjusting the significance value. Experimental results show that the DPCMB algorithm can adjust the significance value so that the accuracy of the algorithm is comparable to that of the DP algorithm, and running time, score calculation times, and memory requirements of the algorithm are greatly reduced.",

keywords = "Bayesian network structure learning, Dynamic programming, IAMB, Markov blanket",

author = "Tan, {Xiang Yuan} and Gao, {Xiao Guang} and He, {Chu Chao}",

year = "2019",

month = sep,

day = "1",

doi = "10.3969/j.issn.0372-2112.2019.09.012",

language = "繁体中文",

volume = "47",

pages = "1898--1904",

journal = "Tien Tzu Hsueh Pao/Acta Electronica Sinica",

issn = "0372-2112",

publisher = "Chinese Institute of Electronics",

number = "9",

}

TY - JOUR

T1 - 基于马尔科夫毯约束的最优贝叶斯网络结构学习算法

AU - Tan, Xiang Yuan

AU - Gao, Xiao Guang

AU - He, Chu Chao

PY - 2019/9/1

Y1 - 2019/9/1

N2 - To solve the problem about structure learning of optimal Bayesian network, this paper proposes Dynamic Programming Constrained with Markov Blanket (DPCMB), which uses Markov Blanket calculated by Incremental Association Markov Blanket (IAMB) to reduce the number of scoring calculations in Dynamic Programming. We research on the effect of the significance value in IAMB on the performance indicators of DPCMB algorithm, and give reasonable suggestions for adjusting the significance value. Experimental results show that the DPCMB algorithm can adjust the significance value so that the accuracy of the algorithm is comparable to that of the DP algorithm, and running time, score calculation times, and memory requirements of the algorithm are greatly reduced.

AB - To solve the problem about structure learning of optimal Bayesian network, this paper proposes Dynamic Programming Constrained with Markov Blanket (DPCMB), which uses Markov Blanket calculated by Incremental Association Markov Blanket (IAMB) to reduce the number of scoring calculations in Dynamic Programming. We research on the effect of the significance value in IAMB on the performance indicators of DPCMB algorithm, and give reasonable suggestions for adjusting the significance value. Experimental results show that the DPCMB algorithm can adjust the significance value so that the accuracy of the algorithm is comparable to that of the DP algorithm, and running time, score calculation times, and memory requirements of the algorithm are greatly reduced.

KW - Bayesian network structure learning

KW - Dynamic programming

KW - IAMB

KW - Markov blanket

UR - http://www.scopus.com/inward/record.url?scp=85074922125&partnerID=8YFLogxK

U2 - 10.3969/j.issn.0372-2112.2019.09.012

DO - 10.3969/j.issn.0372-2112.2019.09.012

M3 - 文章

AN - SCOPUS:85074922125

SN - 0372-2112

VL - 47

SP - 1898

EP - 1904

JO - Tien Tzu Hsueh Pao/Acta Electronica Sinica

JF - Tien Tzu Hsueh Pao/Acta Electronica Sinica

IS - 9

ER -

基于马尔科夫毯约束的最优贝叶斯网络结构学习算法

Abstract

Access to Document

Other files and links

Fingerprint

Cite this