Table 5 Performance comparison of the proposed MRFGRO based FS algorithm with some popular FS algorithms.
From: MRFGRO: a hybrid meta-heuristic feature selection method for screening COVID-19 using deep features
Optimization algorithm | SARS-CoV-2 CT-scan dataset | COVID-CT dataset | MOSMED dataset | |||
|---|---|---|---|---|---|---|
No. of features | Accuracy (%) | No. of features | Accuracy (%) | No. of features | Accuracy (%) | |
GA | 942 | 92.43 | 779 | 91.11 | 802 | 91.19 |
PSO | 739 | 90.15 | 855 | 94.49 | 864 | 93.29 |
HAS | 1011 | 94.17 | 814 | 92.23 | 743 | 92.29 |
ASO | 898 | 97.57 | 957 | 95.59 | 601 | 91.11 |
EO | 917 | 96.69 | 913 | 96.28 | 698 | 90.19 |
GRO | 868 | 97.79 | 809 | 95.79 | 713 | 93.28 |
MRO | 997 | 97.84 | 877 | 96.78 | 759 | 94.47 |
GA+EO | 942 | 95.48 | 779 | 95.28 | 789 | 94.21 |
PSO+ASO | 1007 | 97.84 | 885 | 92.31 | 728 | 91.37 |
HAS+GRO | 941 | 95.24 | 855 | 95.48 | 738 | 91.27 |
MRFGRO | 875 | 99.42 | 756 | 99.15 | 612 | 95.57 |
