An improved constraint-based Bayesian network learning method using Gaussian kernel probability density estimator

作者：

Highlights：

• Use the (conditional) mutual information to calculate the correlation between different variables.

• Use the entropy estimation approach of Gaussian kernel probability density estimator.

• Do the experiments using the famous Alarm network, verify the improved approach.

摘要

•Use the (conditional) mutual information to calculate the correlation between different variables.•Use the entropy estimation approach of Gaussian kernel probability density estimator.•Do the experiments using the famous Alarm network, verify the improved approach.

论文关键词：Bayesian network,Mutual information,Alarm,Constraint-based structure learning

论文评审过程：Received 27 January 2018, Revised 6 June 2018, Accepted 22 June 2018, Available online 21 July 2018, Version of Record 21 July 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.06.058