Prediction and Impact Analysis of Passenger Flow in Urban Rail Transit in the Postpandemic Era

Table 2

Parameter settings of the GRU neural network.

Parameters	Description	Values
epoch	Number of iterations	100
time_step	Number of timesteps	8
input_size	Dimensions of the input feature vector	6
hidden_size	Dimensions of the hidden feature vector	64
num_layers	Number of hidden layers	1
lr	Learning rate	0.02
optimizer	Type of optimizer	Adam
weight_decay	Coefficient of weight decay	0.001
loss_func	Type of loss function	MSELoss