Research Article
An Adaptive EEG Feature Extraction Method Based on Stacked Denoising Autoencoder for Mental Fatigue Connectivity
Table 1
The parameter setting of the SDAE model.
| | Parameter name | Parameter value |
| | Corrupted fraction probability | 0.5 | | Learning rate | 1 | | Minibatch size | 200 | | Epoch number | 8 | | Node number of the middle layer on the first autoencoder | 8 | | Node number of the middle layer on the second autoencoder | 3 |
|
|
