Prediction and analysis of expressway tunnels crash based on modified convolutional neural network and Shapley additive explanations
Proceedings of the Institution of Civil Engineers - Transport · 14.11.2025 · 178 (7) · 502-515
DOI: 10.1680/jtran.24.00129 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Institution of Civil Engineers - Transport, online erschienen am 24.01.2025. Verfasst von Yonghong Yang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: Key Area Research and Development Programme of Guangdong Province, Guangdong Basic and Applied Basic Research Foundation, Open Fund of the Key Laboratory of Highway Engineering of Ministry of Education.
Abstract (Originalsprache)
The prediction and analysis of traffic crashes in expressway tunnels plays a pivotal role in enhancing tunnel safety. A modified convolutional neural network (M-CNN) for tunnel traffic crash prediction was developed in this study. The synthetic minority over-sampling technique was used to address the issue of imbalanced crash data. Based on the prediction results, sections of high risk in tunnels were identified and Shapley additive explanations (Shap) were used to enhance the interpretability of the M-CNN. The results showed that the prediction accuracy of the M-CNN is high (74.62%) and surpassed the accuracy of baseline models (convolutional neural network, back-propagation neural network, random forest, long short-term memory and support vector machine). The tunnel entrance and exit sections were identified as risk zones. In addition, driver’s operation, tunnel grade and vehicle speed were found to have the greatest impact on rear-end crashes, sideswipe crashes and hitting guardrail crashes, respectively. This study also revealed intricate interaction effects between the variables and the skidding resistance index, with this index exhibiting a negative correlation with crash risk. The research findings have significant implications for the future implementation of machine learning models in crash studies, with practical applications for reducing crash rates.
Förderung
- Key Area Research and Development Programme of Guangdong Province
- Guangdong Basic and Applied Basic Research Foundation
- Open Fund of the Key Laboratory of Highway Engineering of Ministry of Education
Zitieren
APA
Yang, Y., Zheng, T., Zhang, Y., Jiang, Y., & Hu, Y. (2025). Prediction and analysis of expressway tunnels crash based on modified convolutional neural network and Shapley additive explanations. Proceedings of the Institution of Civil Engineers - Transport, 178(7), 502-515. https://doi.org/10.1680/jtran.24.00129
Vancouver
Yang Y, Zheng T, Zhang Y, Jiang Y, Hu Y. Prediction and analysis of expressway tunnels crash based on modified convolutional neural network and Shapley additive explanations. Proceedings of the Institution of Civil Engineers - Transport. 2025;178(7):502-515. doi:10.1680/jtran.24.00129
BibTeX
@article{Yang2025,
author = {Yang, Yonghong and Zheng, Tao and Zhang, Yu and Jiang, Yi and Hu, Yixi},
title = {Prediction and analysis of expressway tunnels crash based on modified convolutional neural network and Shapley additive explanations},
journal = {Proceedings of the Institution of Civil Engineers - Transport},
year = {2025},
volume = {178},
number = {7},
pages = {502--515},
doi = {10.1680/jtran.24.00129}
}
EUVIMED