A parallel metaheuristic approach for ensemble feature selection based on multi-core architectures

作者：

Highlights：

• Parallel heterogeneous ensemble feature selection approaches are proposed.

• A multi-core technologies are used to accelerate the ensemble feature selection.

• Experimental evaluations are conducted using Twenty-one well-known large datasets.

• Comparative evaluation shows superiority of the proposed approaches.

摘要

•Parallel heterogeneous ensemble feature selection approaches are proposed.•A multi-core technologies are used to accelerate the ensemble feature selection.•Experimental evaluations are conducted using Twenty-one well-known large datasets.•Comparative evaluation shows superiority of the proposed approaches.

论文关键词：Meta-heuristics,Evolutionary computation,Parallel processing,Feature selection,Ensemble learning

论文评审过程：Received 17 June 2020, Revised 15 May 2021, Accepted 24 May 2021, Available online 31 May 2021, Version of Record 10 June 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115290