JZUS - Journal of Zhejiang University SCIENCE

Frontiers of Information Technology & Electronic Engineering

Accepted manuscript available online (unedited version)

MltAuxTSPP: a unified benchmark for deep learning-based traffic state prediction with multi-source auxiliary data

Author(s): Yusong ZHOU^1, ², Xiaoyu JIANG^1, ², Shu SUN^1, ², Xinmin ZHANG^1, ², Yuanqiu MO³, Zhihuan SONG^1, ²
Affiliation(s): ¹College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China ²State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China ³Mathematics department, Southeast University, Nanjing 211189, China
Corresponding email(s): zhoushichan@zju.edu.cn, jiangxiaoyu@zju.edu.cn, shusun@zju.edu.cn, xinminzhang@zju.edu.cn
Key Words: Traffic prediction; Benchmark platform; Deep learning; Multi-source auxiliary data

Share this article to： More <<< Previous Paper \|Next Paper >>>

Yusong ZHOU^1,², Xiaoyu JIANG^1,², Shu SUN^1,²,Xinmin ZHANG^1,², Yuanqiu MO³, Zhihuan SONG^1,². MltAuxTSPP: a unified benchmark for deep learning-based traffic state prediction with multi-source auxiliary data[J]. Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/FITEE.2500169

@article{title="MltAuxTSPP: a unified benchmark for deep learning-based traffic state prediction with multi-source auxiliary data",
author="Yusong ZHOU^1,², Xiaoyu JIANG^1,², Shu SUN^1,²,Xinmin ZHANG^1,², Yuanqiu MO³, Zhihuan SONG^1,²",
journal="Frontiers of Information Technology & Electronic Engineering",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/FITEE.2500169"
}

%0 Journal Article
%T MltAuxTSPP: a unified benchmark for deep learning-based traffic state prediction with multi-source auxiliary data
%A Yusong ZHOU^{1
%A ²}
%A Xiaoyu JIANG^{1
%A ²}
%A Shu SUN^{1
%A ²}
%A Xinmin ZHANG^{1
%A ²}
%A Yuanqiu MO³
%A Zhihuan SONG^{1
%A ²}
%J Frontiers of Information Technology & Electronic Engineering
%P
%@ 2095-9184
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/FITEE.2500169"

TY - JOUR
T1 - MltAuxTSPP: a unified benchmark for deep learning-based traffic state prediction with multi-source auxiliary data
A1 - Yusong ZHOU^{1
A1 - ²}
A1 - Xiaoyu JIANG^{1
A1 - ²}
A1 - Shu SUN^{1
A1 - ²}
A1 - Xinmin ZHANG^{1
A1 - ²}
A1 - Yuanqiu MO³
A1 - Zhihuan SONG^{1
A1 - ²}
J0 - Frontiers of Information Technology & Electronic Engineering
SP -
EP -
%@ 2095-9184
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/FITEE.2500169"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: Deep learning has empowered traffic prediction models to integrate diverse auxiliary data sources, such as weather and temporal information, for enhanced forecasting accuracy. However, existing approaches often suffer from limited generality and scalability, and the field lacks a unified benchmark for fair model comparison. This absence hinders consistent performance evaluation, slows the development of robust and adaptable models, and makes it challenging to quantify the incremental benefits of different auxiliary data sources. To address these issues, we present MltAuxTSPP, a unified benchmark framework for deep learning-based traffic state prediction with multi-source auxiliary data. The framework features a standardized data container and a fusion embedding module, which enable consistent utilization of heterogeneous data and improve scalability. It produces unified hidden representations that can be seamlessly adopted by various downstream models, ensuring fair and reproducible comparisons under identical conditions. Extensive experiments on real-world datasets demonstrate that MltAuxTSPP effectively leverages weather and temporal features to improve long-term forecasting performance and offers a practical and reproducible foundation for advancing research in traffic state prediction.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference