Interpretable Traffic Accident Prediction: Attention Spatial–Temporal Multi-Graph Traffic Stream Learning Approach

Traffic accident prediction plays a vital role in Intelligent Transportation Systems (ITS), where a large number of traffic streaming data are generated on a daily basis for spatiotemporal big data analysis. The rarity of accidents and the absent interconnection information make it hard for spatiotemporal modeling. Moreover, the inherent characteristic of the black box predictive model makes it difficult to interpret the reliability and effectiveness of the deep learning model. To address these issues, a novel self-explanatory spatial-temporal deep learning model–Attention Spatial-Temporal Multi-Graph Convolutional Network (ASTMGCN) is proposed for traffic accident prediction. The original recorded rare accident data is formulated as a multivariate irregularly interval-aligned dataset, and the temporal discretization method is used to transfer into regularly sampled time series. Multiple graphs are defined to construct edge features and represent spatial relationships when node-related information is missing. Multi-graph convolutional operators and attention mechanisms are integrated into a Sequence-to-Sequence (Seq2Seq) framework to effectively capture dynamic spatial and temporal features and correlations in multi-step prediction. Comparative experiments and interpretability analysis are conducted on a real-world data set, and results indicate that our model can not only yield superior prediction performance but also has the advantage of interpretability.

• Record URL:
  • http://dx.doi.org/10.1109/TITS.2024.3435995
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/41297384
• Supplemental Notes:
  • Copyright © 2024, IEEE.
• Authors:
  • Li, Chaojie
  • 0000-0002-0557-1481
  • Zhang, Borui
  • Wang, Zeyu
  • Yang, Yin
  • Pan, Shuguo
  • 0000-0003-0724-9020
  • Zhou, Xiaojun
  • Yu, Xinghuo
• Publication Date: 2024-11

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 15574-15586
• Serial:
  • IEEE Transactions on Intelligent Transportation Systems
  • Volume: 25
  • Issue Number: 11
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 1524-9050
  • Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6979

Subject/Index Terms

• TRT Terms: Data streaming; Machine learning; Predictive models; Time intervals; Traffic crashes
• Subject Areas: Data and Information Technology; Highways; Safety and Human Factors;

Filing Info

• Accession Number: 01944705
• Record Type: Publication
• Files: TRIS
• Created Date: Jan 31 2025 11:45AM