Table 3.
Comparison with other methods.
| Dataset | Work | Accuracy |
|---|---|---|
| KDD Cup 99 | Wu [29] | 85.24 |
| Farahnakian et al. [30] | 96.53 | |
| MGO | 0.9204 | |
| NSL-KDD | Ma et al. [32] SCDNN | 72.64 |
| Javaid et al. [33] STL | 74.38 | |
| Tang et al. [34] DNN | 75.75 | |
| Imamverdiyev et al. [35] Gaussian–Bernoulli RBM | 73.23 | |
| MGO | 76.725 | |
| BIoT | [36] (BiLSTM) | 98.91 |
| Alkadi et al. [36] (NB) | 97.5 | |
| Alkadi et al. [36] (SVM) | 97.8 | |
| Churcher et al. [31] (KNN) | 99 | |
| Churcher et al. [31] (SVM) | 79 | |
| Churcher et al. [31] (DT) | 96 | |
| Churcher et al. [31] (NB) | 94 | |
| Churcher et al. [31] (RF) | 95 | |
| Churcher et al. [31] (ANN) | 97 | |
| Churcher et al. [31] (LR) | 74 | |
| MGO | 99.22 | |
| CICIDS2017 | Vinayakumar [37] | 94.61 |
| Laghrissi et al. [38] | 85.64 | |
| Alkahtani et al. [39] | 80.91 | |
| MGO | 99.941 |