On the Adjacency Matrix of Spatio-Temporal Neural Network Architectures for Predicting Traffic

Sebastian Bomher, Bogdan Ichim, Bogdan Ichim

2023

Abstract

We present in this paper some experiments with the adjacency matrix used as input by three spatio-temporal neural networks architectures when predicting traffic. The architectures were proposed in (Chen et al., 2022), (Li et al., 2018) and (Yu et al., 2018). We find that the predictive power of these neural networks is influenced to a great extent by the inputted adjacency matrix (i.e. the weights associated to the graph of the available traffic infrastructure). The experiments were made using two newly prepared datasets.

Paper Citation

in Harvard Style

Bomher S. and Ichim B. (2023). On the Adjacency Matrix of Spatio-Temporal Neural Network Architectures for Predicting Traffic. In Proceedings of the 9th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS, ISBN 978-989-758-652-1, SciTePress, pages 321-328. DOI: 10.5220/0011971300003479

in Bibtex Style

@conference{vehits23,
author={Sebastian Bomher and Bogdan Ichim},
title={On the Adjacency Matrix of Spatio-Temporal Neural Network Architectures for Predicting Traffic},
booktitle={Proceedings of the 9th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,},
year={2023},
pages={321-328},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011971300003479},
isbn={978-989-758-652-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,
TI - On the Adjacency Matrix of Spatio-Temporal Neural Network Architectures for Predicting Traffic
SN - 978-989-758-652-1
AU - Bomher S.
AU - Ichim B.
PY - 2023
SP - 321
EP - 328
DO - 10.5220/0011971300003479
PB - SciTePress