Modeling Towards Freeway Real-time Traffic Crash Prediction Considering Multi-dimensional Dynamic Feature Interactions

被引：0
|
作者：
Yuan Z.-Z. [1 ]
Hu Y.-R. [1 ]
Yang Y. [2 ]
机构：
[1] School of Traffic and Transportation, Beijing Jiaotong University, Beijing
[2] School of Transportation Science and Engineering, Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control, Beihang University, Beijing
来源：
Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology | 2022年 / 22卷 / 03期
基金：
中国博士后科学基金;
关键词：
Deep & cross network; Deep learning; Freeway; Multidimensional feature interaction; Real- time traffic crash recognition; Traffic engineering;
D O I：
10.16097/j.cnki.1009-6744.2022.03.024
中图分类号：
学科分类号：
摘要：
This paper investigates the impact of weather, road features, and the dynamic mutual interactions among traffic flow, weather, road, and time on the accuracy of real-time crash risk prediction. The study developed four datasets based on the crash data, traffic sensor data, weather data, and road data collected from the Beijing section of the Beijing-Harbin Freeway. The datasets include (1) the simple traffic flow data; (2) the combined traffic flow, weather, and time data; (3) the combined traffic flow, road, and time data; (4) combined traffic flow, weather, road, and time data. By considering the interactions of multi-dimensional dynamic features, this study proposes a real-time crash risk prediction model based on the Deep & Cross Network (DCN). The results demonstrate that the DCN model achieves higher accuracy than other methods in real-time crash risk prediction. The Area Under Curve (AUC) of the model is 0.8562 and the proposed model is able to correctly classify 84.26% of non-crash data and 77.55% of crash data with the probability threshold of 0.2. The DCN model used in this study can effectively predict the occurrence of freeway crashes and collisions in time, under the condition of multi-dimensional dynamic feature interactions. The proposed method has great potential to support the freeway safety management departments of China in both theoretical and technical aspects. Copyright © 2022 by Science Press.
引用
收藏
页码：215 / 223
页数：8
相关论文
共 18 条
  • [1] Outline of building a strong transportation country
  • [2] YANG Y., Research on the method of freeway crash risk identification and comprehensive traffic safety evaluation considering the regional type difference, (2020)
  • [3] YANG Y, YUAN Z Z, WANG Y H, Freeway crash risk identification based on WOMDIapriori algorithm, Traffic Engineering, 21, 6, pp. 1-10, (2021)
  • [4] WANG K., Analysis and prediction of the severity of freeway traffic accidents under the influence of roads and the environment, (2021)
  • [5] LORD D., Modeling motor vehicle crashes using poisson gamma models: Examining the effects of low sample mean values and small sample size on the estimation of the fixed dispersion parameter, Accident Analysis & Prevention, 38, 4, pp. 751-766, (2006)
  • [6] CHEN Y, YUAN H Z, HUANG Z X, Modeling intersection traffic crashes using a zerotruncated negative binomial model, China Journal of Highway and Transport, 33, 4, pp. 146-154, (2020)
  • [7] YOU J M, FANG S E, TANG T, A support vector machine approach on real-time hazardous traffic state detection, Journal of Transportation Systems Engineering and Information Technology, 18, 4, pp. 83-87, (2018)
  • [8] HOSSAIN M, MUROMACHI Y., Understanding crash mechanisms and selecting interventions to mitigate realtime hazards on urban expressways, Transportation Research Record Journal of the Transportation Research Board, 2213, 2213, pp. 53-62, (2011)
  • [9] XU C C., Exploring the relationships between traffic flow states and traffic safety on freeway, (2014)
  • [10] ZHENG Q, XU C, LIU P, Et al., Investigating the predictability of crashes on different freeway segments using the real-time crash risk models, Accident
12