MVCV-Traffic: multiview road traffic state estimation via cross-view learning

Abstract

Fine-grained urban traffic data are often incomplete owing to limitations in sensor technology and economic cost. However, data-driven traffic analysis methods in intelligent transportation systems (ITSs) heavily rely on the quality of input data. Thus, accurately estimating missing traffic observations is an essential data engineering task in ITSs. The complexity of underlying node-wise correlation structures and various missing scenarios presents a significant challenge in achieving high-precision estimation. This study proposes a novel multiview neural network termed MVCV-Traffic, equipped with a cross-view learning mechanism, to improve traffic estimation. The contributions of this model can be summarized into two parts: multiview learning and cross-view fusing. For multiview learning, several specialized neural networks are adopted to fit diverse correlation structures from different views. For cross-view fusing, a new information fusion strategy merges multiview messages at both feature and output levels to enhance the learning of joint correlations. Experiments on two real-world datasets demonstrate that the proposed model significantly outperforms existing traffic speed estimation methods for different types and rates of missing data.

Keywords:

• Traffic estimation
• intelligent transportation system
• multiview learning

Acknowledgments

The authors would like to thank Liang Xu for helping to collect the data. This work was carried out in part using computing resources at the High Performance Computing Platform of Central South University.

Data and codes availability statement

The data and codes that support the findings of this study are available at https://github.com/at932/MVCV-Traffic.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This project was supported by the National Natural Science Foundation (NSFC) of China under Grant 42171459 and Grant 42071452, the Hunan Provincial Natural Science Foundation of China under Grant 2022JJ20059, the Hunan Provincial Innovation Foundation for Postgraduate under Grant CX20230157 and the Central South University Innovation-Driven Research Program under Grant 2023CXQD013.

Notes on contributors

Min Deng

Min Deng received Ph.D. degrees from Wuhan University in 2003 and the Asian Institute of Technology in 2004. He is currently a doctoral supervisor and associate dean of the School of Geosciences and Info-Physics, Central South University.

Kaiqi Chen

Kaiqi Chen received a B.S. degree in 2018 from Central South University, Changsha, China. He is currently pursuing a doctorate degree with the School of Geosciences and Info-Physics, Central South University. His research interests include data mining and machine learning.

Kaiyuan Lei

Kaiyuan Lei received a B.S. degree in 2021. She is pursuing a Ph.D. at the School of Geosciences and Info-Physics, Central South University, Changsha, China. Her research interests include uncertainty in spatiotemporal data mining.

Yuanfang Chen

Yuanfang Chen is a graduate student at Central South University, and her research interests focus on spatiotemporal association rule mining and crime analysis.

Yan Shi

Yan Shi received a Ph.D. degree from Central South University, Changsha, China, in 2015. He is currently an associate professor with the School of Geosciences and Info-Physics and a master supervisor at the School of Geosciences and Info-Physics, Central South University.