Using high-fidelity meta-models to improve performance of small dataset trained Bayesian Networks

作者：

Highlights：

• Bayesian Networks often cannot be used with small datasets due to accuracy concerns.

• Kriging and radial-basis function meta-models are viable options for augmenting datasets.

• Bayesian network accuracy increases when using meta-model generated data.

摘要

•Bayesian Networks often cannot be used with small datasets due to accuracy concerns.•Kriging and radial-basis function meta-models are viable options for augmenting datasets.•Bayesian network accuracy increases when using meta-model generated data.

论文关键词：Machine learning,Bayesian Networks,Small datasets,Meta-models,Data generation

论文评审过程：Received 3 July 2018, Revised 7 July 2019, Accepted 19 July 2019, Available online 20 July 2019, Version of Record 5 August 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.112830