Table 1 Specific parameters of convolutional neural network.

From: A multi-information fusion anomaly detection model based on convolutional neural networks and AutoEncoder

Network layer

Input

Convolution kernel

Output

Convolution layer-1

1 × 1600

1 × 25

32 × 1600

Maximum pooling

32 × 1600

1 × 5

32 × 320

Convolution layer-2

32 × 320

1 × 25

64 × 320

Maximum pooling

64 × 320

1 × 5

64 × 64

Fully Connected Layer-1

4096

–

1024

Fully Connected Layer-2

1024

–

600

Back to article page