Stress Classification Using Brain Signals Based on LSTM Network

Table 2

Parameters for LSTM models chosen after hyperparameter tuning.

Parameter	Values
Number of input features	20
Number of output features	1
Number of LSTM layers	2
Number of hidden units in LSTM layers	8 and 16 (only for two-layer LSTM)
Activation function	Sigmoid
Optimizer	Adam
Loss function	Binary cross entropy
Batch size	32
Window size	20
Epochs	100
Dropout value	0.2