Skip to main content

Table 8 Layers of final classifier neural network for SCADA dataset

From: A machine-learning phase classification scheme for anomaly detection in signals with periodic characteristics

  Layer type Sizes
0 Convolutional M(0)=4, T(0)=3,
1 Max pooling M(1)=24, T(1)=3,
2 Convolutional M(2)=24, T(2)=3,
   M(3)=72, T(3)=3
3 Fully connected N(3)=216
4 Fully connected N(4)=29
5 Output N(5)=4