A robust multiobjective Harris’ Hawks Optimization algorithm for the binary classification problem

作者：

Highlights：

• We propose a multiobjective Harris’ Hawks Optimization algorithm (MHHO).

• MHHO minimizes the number of features and maximizes the classification accuracy.

• New discrete optimization operators are proposed for exploration and exploitation.

• Experiments are performed on 13 benchmark UCI datasets and a COVID-19 dataset.

• Solutions of MHHO are competitive with the state-of-the-art metaheuristics.

摘要

•We propose a multiobjective Harris’ Hawks Optimization algorithm (MHHO).•MHHO minimizes the number of features and maximizes the classification accuracy.•New discrete optimization operators are proposed for exploration and exploitation.•Experiments are performed on 13 benchmark UCI datasets and a COVID-19 dataset.•Solutions of MHHO are competitive with the state-of-the-art metaheuristics.

论文关键词：Binary classification,Multiobjective optimization,Feature selection,Harris’ Hawks optimization

论文评审过程：Received 19 November 2020, Revised 22 April 2021, Accepted 9 June 2021, Available online 12 June 2021, Version of Record 16 June 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.107219