A Comparative Study of Graph Neural Network Speed Prediction during Periods of Congestion

Marko Oosthuizen, Marko Oosthuizen, Alwyn J. Hoffman, Marelie Davel, Marelie Davel, Marelie Davel

2022

Abstract

Traffic speed prediction using deep learning has been the topic of many studies. In this paper, we analyse the performance of Graph Neural Network-based techniques during periods of traffic congestion. We first compare a selection of recently proposed techniques that claim to achieve good results using the METR-LA and PeMS-BAY data sets. We then investigate the performance of three of these approaches – Graph WaveNet, Spacetime Neural Network (STNN) and Spatio-Temporal Attention Wavenet (STAWnet) – during congested periods, using recurrent congestion patterns to set a threshold for general congestion through the entire traffic network. Our results show that performance deteriorates significantly during congested time periods, which is concerning, as traffic speed prediction is usually of most value during times of congestion. We also found that, while the above approaches perform almost equally in the absence of congestion, there are much bigger differences in performance during periods of congestion.

Paper Citation

in Harvard Style

Oosthuizen M., J. Hoffman A. and Davel M. (2022). A Comparative Study of Graph Neural Network Speed Prediction during Periods of Congestion. In Proceedings of the 14th International Joint Conference on Computational Intelligence (IJCCI 2022) - Volume 1: NCTA; ISBN 978-989-758-611-8, SciTePress, pages 331-338. DOI: 10.5220/0011374100003332

in Bibtex Style

@conference{ncta22,
author={Marko Oosthuizen and Alwyn J. Hoffman and Marelie Davel},
title={A Comparative Study of Graph Neural Network Speed Prediction during Periods of Congestion},
booktitle={Proceedings of the 14th International Joint Conference on Computational Intelligence (IJCCI 2022) - Volume 1: NCTA},
year={2022},
pages={331-338},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011374100003332},
isbn={978-989-758-611-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computational Intelligence (IJCCI 2022) - Volume 1: NCTA
TI - A Comparative Study of Graph Neural Network Speed Prediction during Periods of Congestion
SN - 978-989-758-611-8
AU - Oosthuizen M.
AU - J. Hoffman A.
AU - Davel M.
PY - 2022
SP - 331
EP - 338
DO - 10.5220/0011374100003332
PB - SciTePress