Table 6 Comparison of the proposed method with some state-of-the-art methods on COVID-CT dataset.
From: MRFGRO: a hybrid meta-heuristic feature selection method for screening COVID-19 using deep features
Work Ref. | Feature | Method of classification | Obtained accuracy (%) |
|---|---|---|---|
Loey et al.49 | Deep features | Data augmentation with classical augmentation technique and CGAN | 82.91 |
Sakagianni et al.50 | NA | AutoML Cloud Version | 88.31 |
Jhao et al.32 | Pre-trained CNN learns by itself | TL by DenseNet161 + CSSL | 89.1 |
Alshazly et al.47 | Transfer learning | DenseNet201 | 92.2 |
Shaban et al.46 | GLCM | HFSM and KNN classifier | 96 |
Saeedi et al.21 | Deep features of DenseNet121 | Nu-SVM | 90.61 ± 5 |
Proposed algorithm | Deep features of ResNet18 and GoogLeNet | MRFGRO based FS algorithm | 99.15 |
