Table 3.
The architecture of 1-D CNN.
| Layers | Type | Activation function | Number of neurons (output layer) | Filter size | Number of filters | Stride |
|---|---|---|---|---|---|---|
| 1 | Input | 250 × 1 | ||||
| 2 | Convolution | ReLU | 246 × 4 | 5 × 1 | 4 | 1 |
| 3 | Max-pooling | 123 × 4 | 2 × 1 | 4 | 2 | |
| 4 | Convolution | ReLU | 120 × 4 | 4 × 1 | 4 | 1 |
| 5 | Max-pooling | 60 × 4 | 2 × 1 | 4 | 2 | |
| 6 | Convolution | ReLU | 56 × 4 | 5 × 1 | 4 | 1 |
| 7 | Max-pooling | 28 × 4 | 2 × 1 | 4 | 2 | |
| 8 | Convolution | ReLU | 24 × 8 | 5 × 1 | 8 | 1 |
| 9 | Max-pooling | 12 × 8 | 2 × 1 | 8 | 2 | |
| 10 | Fully connected | ReLU | 10 | |||
| 11 | Output | SoftMax | 5 |