Research Article
Feature Selection Based on Cross-Correlation for the Intrusion Detection System
Table 9
Results of the CCFS method on different datasets for accuracy, precision, recall, and F1-score criteria.
| Classification method | KDD Cup 99 | NSL-KDD | AWID | CIC-IDS2017 | DT | SVM | KNN | NB | DT | SVM | KNN | NB | DT | SVM | KNN | NB | DT | SVM | KNN | NB |
| Accuracy | 85.19 | 84.66 | 84.66 | 84.06 | 93.47 | 90.69 | 93.09 | 90.87 | 98.42 | 96.75 | 97.84 | 95.53 | 97.91 | 97.12 | 97.24 | 96.32 | Precision | 86.45 | 85.53 | 85.97 | 85.37 | 94.87 | 92.39 | 94.39 | 92.27 | 98.49 | 96.51 | 97.87 | 95.55 | 99.42 | 98.23 | 98.75 | 96.62 | Recall | 86.43 | 85.63 | 85.92 | 85.16 | 95.79 | 92.12 | 94.35 | 92.27 | 98.35 | 96.51 | 97.87 | 96.08 | 99.07 | 97.94 | 98.75 | 96.61 | F1-score | 86.44 | 85.58 | 85.95 | 85.27 | 95.33 | 92.25 | 94.37 | 92.27 | 98.42 | 96.51 | 97.87 | 95.81 | 99.24 | 98.09 | 98.75 | 96.62 |
|
|