Table 3 Details of python libraries, hyper parameter settings and hardware specifications.

From: Gaussian dual adjacency graph based spatial correlated and temporal time dependent traffic prediction in Bangalore City

Python libraries

Version

Python

3.10.11

Numpy

1.25.2

Pandas

2.0.3

Scikit-learn

1.3.0

Tensorflow

2.13.0 (or pytorch 2.0.1)

Matplotlib

3.7.2

seaborn

0.12.2

Hyper parameter settings

Learning rate

0

Batch size

32

Optimizer

Adam, ε = 1e-8

Dropout rate

0.5

Number of epochs

50

Regularization

L2 weight decay = 1e-4

Loss function

Cross-entropy/MSE/custom loss

Convergence criteria

Fixed epochs

50

Early stopping

Stop if validation loss doesn’t improve for 10 epochs

Hardware specifications

Operating systems

Windows 10 and above

Processors

Intel® Core™ i5-9600 Processor; 9 M Cache, up to 4.60 GHz

Memory (RAM)

8 GB

Storage (HDD)

500 GB and above