Research Article
Effective Anomaly Detection Using Deep Learning in IoT Systems
Table 6
Performance of the binary classifier varying the number of features through PCA and autoencoders, respectively.
| Features | PCA | AE 3 layers | AE 9 layers | Accuracy | F1 | Accuracy | F1 | Accuracy | F1 |
| 70 | 0.993 | 0.993 | 0.993 | 0.993 | 0.993 | 0.993 | 60 | 0.991 | 0.991 | 0.960 | 0.960 | 0.991 | 0.991 | 50 | 0.992 | 0.992 | 0.964 | 0.964 | 0.994 | 0.994 | 35 | 0.994 | 0.994 | 0.976 | 0.976 | 0.994 | 0.994 | 25 | 0.992 | 0.992 | 0.960 | 0.960 | 0.993 | 0.993 |
|
|