EUVIMEDEUVIMED entdecken
Crossref

MVSTA: Multi-View Spatio-Temporal Correlation Awareness Network for Traffic Data Imputation

Suwen Zhu, Yiheng Ruan, Wei Xiang, Yuanyuan He, Shenghao Liu, Jing Wang, Xianjun Deng

ACM Transactions on Sensor Networks · 30.05.2026 · 22 (3) · 1-24

DOI: 10.1145/3801744 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Sensor Networks, online erschienen am 13.04.2026. Verfasst von Suwen Zhu und 6 weiteren Autor:innen. Die Arbeit nennt 59 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Hubei Provincial Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Road traffic data imputation is an essential component of Intelligent Transportation Systems (ITS). However, the spatio-temporal characteristics in traffic data are complex and diverse, and existing methods are unable to comprehensively extract them. This article, through in-depth observations of traffic system dynamics, innovatively taxonomizes the complex spatio-temporal dependencies into four key dimensions: Geographical Spatial Correlations (GSC), Latent Spatial Correlations (LSC), Intra-sensor Temporal Correlations (ITC), and Cross-sensor Temporal Correlations (CTC). Motivated by this taxonomy, we aim at constructing a novel framework that holistically utilizes these spatio-temporal correlations to improve imputation accuracy. Subsequently, we propose a Multi-View Spatio-Temporal Correlation Awareness Network (MVSTA) for traffic data imputation, which incorporates two specifically designed modules: a Unified Spatial Correlation Awareness module (USCA) and a Collaborative Temporal Correlation Awareness module (CTCA). The USCA integrates GSC and LSC into a unified representation by jointly modeling physical proximity and data-driven dependencies. The CTCA collaboratively extracts ITC and CTC by capturing both local temporal patterns in individual sensors and interactive dynamics across different sensors. Extensive experiments on three real-world traffic datasets demonstrate that MVSTA significantly outperforms all baselines, validating the effectiveness of our proposed taxonomy and framework.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Hubei Provincial Natural Science Foundation of China
  • Hubei Provincial Innovative Scientific and Technological Talents Program of China
  • Self-determined Research Funds of CCNU from the Colleges' basic Research and Operation of MOE
  • Chongqing Natural Science Foundation of China
  • Scientific and Technological Research Program of Chongqing Municipal Education Commission

Zitieren

APA

Zhu, S., Ruan, Y., Xiang, W., He, Y., Liu, S., Wang, J., & Deng, X. (2026). MVSTA: Multi-View Spatio-Temporal Correlation Awareness Network for Traffic Data Imputation. ACM Transactions on Sensor Networks, 22(3), 1-24. https://doi.org/10.1145/3801744

Vancouver

Zhu S, Ruan Y, Xiang W, He Y, Liu S, Wang J, et al. MVSTA: Multi-View Spatio-Temporal Correlation Awareness Network for Traffic Data Imputation. ACM Transactions on Sensor Networks. 2026;22(3):1-24. doi:10.1145/3801744

BibTeX
@article{Zhu2026,
  author = {Zhu, Suwen and Ruan, Yiheng and Xiang, Wei and He, Yuanyuan and Liu, Shenghao and Wang, Jing and Deng, Xianjun},
  title = {MVSTA: Multi-View Spatio-Temporal Correlation Awareness Network for Traffic Data Imputation},
  journal = {ACM Transactions on Sensor Networks},
  year = {2026},
  volume = {22},
  number = {3},
  pages = {1--24},
  doi = {10.1145/3801744}
}
Kostenlos starten →