BMPA-TVSinV: A Binary Marine Predators Algorithm using time-varying sine and V-shaped transfer functions for wrapper-based feature selection

作者：

Highlights：

• A Binary Marine Predator Algorithm (BMPA-TVSinV) is proposed for feature selection.

• Two novel time-varying Sine and V-shaped transfer functions are applied in BMPA.

• The proposed algorithm is evaluated by high-dimensional and COVID-19 datasets.

• BMPA-TVSinV archives a higher accuracy and feature reduction rate on datasets.

摘要

•A Binary Marine Predator Algorithm (BMPA-TVSinV) is proposed for feature selection.•Two novel time-varying Sine and V-shaped transfer functions are applied in BMPA.•The proposed algorithm is evaluated by high-dimensional and COVID-19 datasets.•BMPA-TVSinV archives a higher accuracy and feature reduction rate on datasets.

论文关键词：Feature Selection problem,Time-varying transfer function,Binary Marine Predators Algorithm (BMPA),Classification,COVID-19

论文评审过程：Received 9 May 2022, Revised 5 July 2022, Accepted 8 July 2022, Available online 16 July 2022, Version of Record 28 July 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.109446