MBCGP-FE: A modified balanced cartesian genetic programming feature extractor

作者：

Highlights：

• Discovering hidden relations among features for regular data representation and reducing data dimension.

• Modifying Balanced Cartesian Genetic Programming.

• Determining the size of the new feature space in optimization process.

摘要

•Discovering hidden relations among features for regular data representation and reducing data dimension.•Modifying Balanced Cartesian Genetic Programming.•Determining the size of the new feature space in optimization process.

论文关键词：Feature interaction,Feature extraction,Balanced cartesian genetic programming,Dimensionality reduction

论文评审过程：Received 3 February 2017, Revised 4 August 2017, Accepted 5 August 2017, Available online 15 August 2017, Version of Record 22 September 2017.

论文官网地址：https://doi.org/10.1016/j.knosys.2017.08.005