EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

A multimodal deep learning approach for predicting traffic accident severity using crash records, road geometry, and textual descriptions

Yue Liu, Zhixiang Gao, Hanzhang Ge, Ziyu Chen, Guohua Liang, Yonggang Wang, Yuting Zhang

Computer-Aided Civil and Infrastructure Engineering · 2025-09 · 40 (23) · 3773-3793

DOI: 10.1111/mice.70023 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer-Aided Civil and Infrastructure Engineering, 2025-09. Verfasst von Yue Liu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Liu, Y., Gao, Z., Ge, H., Chen, Z., Liang, G., Wang, Y., & Zhang, Y. (2025). A multimodal deep learning approach for predicting traffic accident severity using crash records, road geometry, and textual descriptions. Computer-Aided Civil and Infrastructure Engineering, 40(23), 3773-3793. https://doi.org/10.1111/mice.70023

Vancouver

Liu Y, Gao Z, Ge H, Chen Z, Liang G, Wang Y, et al. A multimodal deep learning approach for predicting traffic accident severity using crash records, road geometry, and textual descriptions. Computer-Aided Civil and Infrastructure Engineering. 2025;40(23):3773-3793. doi:10.1111/mice.70023

BibTeX
@article{Liu2025,
  author = {Liu, Yue and Gao, Zhixiang and Ge, Hanzhang and Chen, Ziyu and Liang, Guohua and Wang, Yonggang and Zhang, Yuting},
  title = {A multimodal deep learning approach for predicting traffic accident severity using crash records, road geometry, and textual descriptions},
  journal = {Computer-Aided Civil and Infrastructure Engineering},
  year = {2025},
  volume = {40},
  number = {23},
  pages = {3773--3793},
  doi = {10.1111/mice.70023}
}
Kostenlos starten →