Predicting Multiple Traffic Features using a Spatio-Temporal Neural Network Architecture

Bogdan Ichim, Bogdan Ichim, Florin Iordache

2022

Abstract

In this paper we present several experiments done with a complex spatio-temporal neural network architecture, for three distinct traffic features and over four time horizons. The architecture was proposed in (Zhao et al., 2020), in which predictions for a single traffic feature (i.e. speed) were investigated. An implementation of the architecture is available as open source in the StellarGraph library (CSIRO's Data61, 2018). We find that its predictive power is superior to the one of a simpler temporal model, however it depends on the particular feature predicted. All experiments were performed with a new dataset, which was prepared by the authors.

Paper Citation

in Harvard Style

Ichim B. and Iordache F. (2022). Predicting Multiple Traffic Features using a Spatio-Temporal Neural Network Architecture. In Proceedings of the 8th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS, ISBN 978-989-758-573-9, pages 331-337. DOI: 10.5220/0011062900003191

in Bibtex Style

@conference{vehits22,
author={Bogdan Ichim and Florin Iordache},
title={Predicting Multiple Traffic Features using a Spatio-Temporal Neural Network Architecture},
booktitle={Proceedings of the 8th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,},
year={2022},
pages={331-337},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011062900003191},
isbn={978-989-758-573-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,
TI - Predicting Multiple Traffic Features using a Spatio-Temporal Neural Network Architecture
SN - 978-989-758-573-9
AU - Ichim B.
AU - Iordache F.
PY - 2022
SP - 331
EP - 337
DO - 10.5220/0011062900003191