Research Article
Quality-on-Demand Compression of EEG Signals for Telemedicine Applications Using Neural Network Predictors
Table 1
Optimal configuration of the network.
| Type of
neural
network |
Predictor
order |
No. of
hidden
neurons |
Activation function | Learning
algorithm | No. of epochs
required for training
(only average is shown) | Hidden
layer | Output
layer | | |
| | SLP | 5 |
â | â | Linear | Levenberg-Marquart (LM) | 65 | | MLP | 3 |
5 | Log-sigmoid | Linear | Levenberg-Marquart (LM) | 230 | | EN | 5 |
5 | Tan-sigmoid | Linear | Gradient descent with momentum and adaptive learning rate back propogation (GDX) | 750 |
|
|
