Research Article
Lightweight Intrusion Detection Model of the Internet of Things with Hybrid Cloud-Fog Computing
Table 9
Experimental results of BoT-IoT in various types.
| Model | Metrics | 0 | 1 | 2 | 3 | 4 |
| TP2SF [17] | Precision | 1.0000 | 0.8700 | 1.0000 | 0.7400 | 0.0000 | Recall | 0.8500 | 0.9800 | 0.8300 | 1.0000 | 0.0000 | F1-score | 0.9200 | 0.9200 | 0.9000 | 0.8500 | 0.0000 |
| Sp2f [18] | Precision | 0.9981 | 1.0000 | 1.0000 | 0.9972 | 1.0000 | Recall | 1.0000 | 0.9981 | 0.9997 | 0.9998 | 0.7083 | F1-score | 0.9990 | 0.9990 | 0.9998 | 0.9985 | 0.8292 |
| ConvNeXt | Accuracy | 1.0000 | 1.0000 | 1.0000 | 1.0000 | 1.0000 | Precision | 1.0000 | 1.0000 | 0.9811 | 0.9998 | 1.0000 | Recall | 1.0000 | 1.0000 | 0.9630 | 0.9999 | 1.0000 | F1-score | 1.0000 | 1.0000 | 0.9720 | 0.9999 | 1.0000 | FAR | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| Proposed model | Accuracy | 1.0000 | 1.0000 | 1.0000 | 1.0000 | 1.0000 | Precision | 1.0000 | 1.0000 | 0.9811 | 1.0000 | 1.0000 | Recall | 1.0000 | 1.0000 | 1.0000 | 0.9999 | 1.0000 | F1-score | 1.0000 | 1.0000 | 0.9905 | 1.0000 | 1.0000 | FAR | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
|
|
The bold value in the table means that the corresponding model is optimal on this performance metric.
|