Research Article
Elephant Flows Detection Using Deep Neural Network, Convolutional Neural Network, Long Short-Term Memory, and Autoencoder
Table 6
Comparison of deep learning algorithm.
| Algorithm | Performance in accuracy | Model run time | Loss | Dataset used | #Parameters |
| DNN | 99.12% in average | 4 s | 0.041 | NIMS, Unicauca, and SDN | NIMS-24, SDN-21, and Unicauca-75 | CNN | 98.49% | 5 s 3 ms | 0.015 | SDN | 21 | LSTM | 98.78% | 57 s 60 ms | 0.03 | SDN | 21 | Deep autoencoder | 97.95% | 59 s | 0.13 | SDN | 21 |
|
|