Table 4. Absence of impact on performance of the increase of neurons and hidden layers for artificial neural network (ANN).

Example of the performance assessed by the F score on the balanced test dataset 3 (see Table 2).

ANN
Error minimization algorithm		Stochastic Gradient-Descent (SGD)
Activation function		Logistic Sigmoid
Regularization		No
Nb hidden layers (n)		1			2			3
Neurons/hidden layer (n)		10	50	100	10	50	100	10	50	100
F-score	5minSpO2 class 1	0.25	0.25	0.25	0.25	0.25	0.25	0.22	0.22	0.19
	5minSpO2 class 2	0.33	0.33	0.33	0.33	0.33	0.33	0.33	0.33	0.32
	5minSpO2 class 3	0.72	0.72	0.72	0.72	0.72	0.72	0.69	0.69	0.69