Table 5.

AE implementation details.

Hyper-parameters	Values
Input dimension	$39\times 1$ (39 medical features)
Number of neurons of the first layer	$39\times 1$
Number of neurons of the second layer	$32\times 1$
Number of neurons of the third layer	$39\times 1$
First and second layers activation function	ReLU
Third layer activation function	Sigmoid
Adam hyper-parameters	${\beta }_1=0.9,{\beta }_2=0.999$
Learning rate	0.001
Loss function	Binary cross entropy (BCE)
Number of epochs	100