Skip to main content

Table 5 Layers of final classifier neural network for ECG dataset

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

 

Layer type

Sizes

0

Convolutional

M(0)=15, T(0)=17,

  

S(0)=7

1

Max pooling

M(1)=90, T(1)=17,

  

R(1)=3

2

Convolutional

M(2)=90, T(2)=6,

  

S(2)=5

  

M(3)=270, T(3)=6

3

Fully connected

N(3)=1620

4

Fully connected

N(4)=80

5

Output

N(5)=4