Learning Optimal Bayesian Network Structure Constrained with Markov Blanket

TAN Xiang-yuan; GAO Xiao-guang; HE Chu-chao

doi:10.3969/j.issn.0372-2112.2019.09.012

您当前的位置：

首页 >

文章列表页 >

Learning Optimal Bayesian Network Structure Constrained with Markov Blanket

更新时间：2025-07-16

- Learning Optimal Bayesian Network Structure Constrained with Markov Blanket
- Acta Electronica Sinica Vol. 47, Issue 9, Pages: 1898-1904(2019)
- 作者机构：
  
  西北工业大学电子信息学院,陕西,西安,710129
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61573285)
- DOI：10.3969/j.issn.0372-2112.2019.09.012
  CLC： TP18
- Published Online：25 September 2019，
  
  Published：2019
- 稿件说明：
移动端阅览
TAN Xiang-yuan, GAO Xiao-guang, HE Chu-chao. Learning Optimal Bayesian Network Structure Constrained with Markov Blanket[J]. Acta Electronica Sinica, 2019, 47(9): 1898-1904.
DOI：

TAN Xiang-yuan, GAO Xiao-guang, HE Chu-chao. Learning Optimal Bayesian Network Structure Constrained with Markov Blanket[J]. Acta Electronica Sinica, 2019, 47(9): 1898-1904. DOI： 10.3969/j.issn.0372-2112.2019.09.012.

摘要

本文针对最优贝叶斯网络的结构学习问题，在动态规划算法（Dynamic Programming，DP）的基础上，使用IAMB算法（Incremental Association Markov Blanket，IAMB）计算得到的马尔科夫毯对评分计算过程进行约束，减少了评分的计算次数，提出了基于马尔科夫毯约束的动态规划算法（Dynamic Programming Constrained with Markov Blanket，DPCMB），研究了IAMB算法中重要性阈值对DPCMB算法的各项性能指标的影响，给出了调整阈值的合理建议.实验结果表明，DPCMB算法可以通过调整重要性阈值，使该算法的精度与DP算法相当，极大地减少了算法的运行时间、评分计算次数和所需存储空间.

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.

关键词

Keywords

references

Views

274

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Optimal BN Structure Learning Algorithm Based on Double Constraints

Local-Global LWF Chain Graph Structure Learning Algorithm Based on Constraints

Related Author

XU Wen

ZHANG Huan

ZHANG Xin-lan

WANG Peng

DI Ruo-hai

CHEN Yi-wei

YU Kui

WANG Yun-xia

Related Institution

School of Electronics and Information Engineering, Xi'an Technological University, , Shannxi

Aerospace Research Institute of Materials & Processing Technology

School of Computer and Information Technology， Shanxi University

School of Computer Science and Information Engineering， Hefei University of Technology

⁰