CovH2SD: A COVID-19 detection approach based on Harris Hawks Optimization and stacked deep learning

作者：

Highlights：

• Proposing HHO deep learning approach for COVID-19 detection using chest CT images.

• Applying transfer learning using 9 pre-trained convolutional neural network models.

• Injecting HHO in learning process to select optimal configurations for each model.

• Presenting a stacking mechanism from the optimized models.

• The proposed approach is benchmarked against other state-of-the-art models.

摘要

•Proposing HHO deep learning approach for COVID-19 detection using chest CT images.•Applying transfer learning using 9 pre-trained convolutional neural network models.•Injecting HHO in learning process to select optimal configurations for each model.•Presenting a stacking mechanism from the optimized models.•The proposed approach is benchmarked against other state-of-the-art models.

论文关键词：Computed Tomography (CT),Convolutional Neural Network (CNN),COVID-19,Data Augmentation (DA),Harris Hawks Optimization (HHO),Transfer Learning (TL)

论文评审过程：Received 26 June 2021, Revised 13 August 2021, Accepted 23 August 2021, Available online 5 September 2021, Version of Record 9 September 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115805