Research Article
Building an Effective Intrusion Detection System by Using Hybrid Data Optimization Based on Machine Learning Algorithms
Table 7
Comparison between DO_IDS and RF on Precision, Recall, and F1-score.
| ā | Precision | Recall | F1-score | RF | DO_IDS | RF | DO_IDS | RF | DO_IDS |
| Normal | 0.859 | 0.897 | 0.876 | 0.967 | 0.867 | 0.930 | Generic | 0.997 | 0.998 | 0.967 | 0.969 | 0.982 | 0.983 | Exploits | 0.687 | 0.759 | 0.697 | 0.663 | 0.692 | 0.708 | Fuzzers | 0.055 | 0.942 | 0.029 | 0.381 | 0.038 | 0.542 | Reconnaissance | 0.886 | 0.888 | 0.814 | 0.820 | 0.849 | 0.853 | DoS | 0.327 | 0.351 | 0.417 | 0.461 | 0.367 | 0.399 | Analysis | 0.002 | 0.046 | 0.003 | 0.061 | 0.002 | 0.053 | Backdoor | 0.040 | 0.151 | 0.063 | 0.403 | 0.049 | 0.219 | Shellcode | 0.242 | 0.352 | 0.817 | 0.780 | 0.373 | 0.486 | Worms | 0.800 | 0.778 | 0.182 | 0.795 | 0.296 | 0.787 |
|
|