Skip to main content
. 2019 Jan 18;19(2):384. doi: 10.3390/s19020384

Table 8.

Parameters of MLPNN-based pain status classifier model.

Structure from Input Layer to Output Layer 15-6-6-2
Number of features 15
Number of hidden layers 2
Number of hidden neurons on the hidden layers 6
Learning rate for hidden layers 0.08
Number of batch size 104
Number of epoch in the training 800
Weight decay 0.00029
Activation function sigmoid function