Table 3 The results of binary classification using features selected by the MCP algorithm.
Method | NF-CSE-CIC-IDS2018-v2 | NF-ToN-IoT-v2 | NF-UNSW-NB15-v2 | NF-BoT-IoT-v2 | CIC-ToN-IoT | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
num | F1 | Acc | num | F1 | Acc | num | F1 | Acc | num | F1 | Acc | num | F1 | Acc | |
Fast-mRMR | 33 | 0.995 | 0.995 | 35 | 0.991 | 0.991 | 36 | 0.997 | 0.997 | 23 | 0.998 | 0.998 | 43 | 0.993 | 0.993 |
CMA-ES | 21 | 0.995 | 0.995 | 26 | 0.991 | 0.991 | 22 | 0.997 | 0.997 | 17 | 0.998 | 0.998 | 36 | 0.993 | 0.993 |
GA | 23 | 0.995 | 0.995 | 26 | 0.991 | 0.991 | 25 | 0.997 | 0.997 | 22 | 1.0 | 1.0 | 41 | 0.993 | 0.993 |
PSO | 20 | 0.995 | 0.995 | 25 | 0.991 | 0.991 | 19 | 0.997 | 0.997 | 24 | 0.928 | 0.872 | 39 | 0.993 | 0.993 |
Mohy et al.25 | – | – | – | – | – | – | 24 | 0.992 | 0.993 | – | – | – | – | – | – |
Leevy et al.24 | 9 | 0.990 | 0.990 | 9 | 0.992 | 0.992 | 9 | 0.983 | 0.983 | 9 | 0.989 | 0.987 | – | – | – |
Sarhan et al.9 | 8 | 0.840 | 0.955 | 8 | 1.0 | 0.994 | 8 | 0.850 | 0.985 | – | – | – | – | – | – |
MCP | 9 | 0.995 | 0.995 | 7 | 0.990 | 0.990 | 9 | 0.997 | 0.997 | 9 | 0.997 | 0.997 | 13 | 0.993 | 0.993 |
