基于神经网络的实时事故预测方法研究进展

doi:10.16638/j.cnki.1671-7988.2024.005.036

摘要/Abstract

摘要： 道路交通事故预测作为道路主动安全管理的重要组成部分，在降低事故发生概率、帮助管理者制定安全决策等方面起着重要作用。随着数据需求的不断增加，传统方法已无法满足大数据的需求，机器学习和人工智能算法在动态、实时和复杂情况下的道路交通事故预测领域显示出强大的潜力。文章从数据获取和特征变量选择开始介绍，详细叙述了基于机器学习的神经网络及与深度学习结合后该方法在国内外的相关研究，分析了使用神经网络相关方法在建模时会面临的优缺点，最后对基于神经网络的交通实时事故预测方法进行了总结及展望，给出未来的发展趋势。

关键词: 交通工程；实时事故预测；神经网络；深度学习

Abstract: As an important part of active road safety management, road traffic accident prediction plays an important role in reducing the probability of accidents and helping managers make safety decisions. With the increasing demand for data, traditional methods can no longer meet the needs of big data, and machine learning and artificial intelligence algorithms have shown strong potential in the field of road traffic accident prediction in dynamic, real-time and complex situations. This paper introduces the data acquisition and the selection of characteristic variables, describes in detail the relevant research of the neural network based on machine learning and the combination of the method with deep learning at home and abroad, analyzes the advantages and disadvantages of using the neural network correlation method in modeling, and finally summarizes and looks forward to the realtime traffic accident prediction method based on neural network, and gives the future development trend.

Key words: Traffic engineering; Real-time accident prediction; Neural network; Deep learning

炎天策. 基于神经网络的实时事故预测方法研究进展[J]. 汽车实用技术, 2024, 49(5): 176-181.

YAN Tiance. Research Progress of Real-time Accident Prediction Methods Based on Neural Networks[J]. Automobile Applied Technology, 2024, 49(5): 176-181.

参考文献

[ 1 ] 张亚丽.世界卫生组织发布《2018 年全球道路安全现状报告》[J].中华灾害救援医学,2019,7(2):100. [ 2 ] ROSHANDEL S,ZHENG Z,WASHINGTON S.Impact of Real-time Traffic Characteristics on Freeway Crash Occurrence:Systematic Review and Meta-analysis[J]. Accident Analysis and Prevention,2015,79:198-211. [ 3 ] 徐铖铖,刘攀,王炜,等.恶劣天气下高速公路实时事故风险预测模型[J].吉林大学学报(工学版),2013, 43(1):68-73. [ 4 ] HOSSAIN M,ABDEL-ATY M,QUDDUS M A,et al. Real-time Crash Prediction Models:State-of-the-art, Design Pathways and Ubiquitous Requirements[J]. Accident Analysis and Prevention,2019,124(3):66-84. [ 5 ] XIAO D,ZHANG B,CHEN Z,et al.Connecting Tradition with Modernity:Safety Literature Review[J]. Digital Transportation and Safety,2023,1(1):2-12. [ 6 ] ABDEL-ATY M,UDDIN N,ABDALLA F,et al.Predicting Freeway Crashes Based on Loop Detector Data Using Matched Case-control Logistic Regression[J]. Transportation Research Record,2004(1):88-95. [ 7 ] ABDEL-ATY M,PANDE A,DAS A,et al.Assessing Safety on Dutch Freeways with Data from Infrastructure-based Intelligent Transportation Systems[J].Transportation Research Record,2008(1):153-161. [ 8 ] ABDEL-ATY M,HASSAN H M,AHMED M,et al. Real-time Prediction of Visibility Related Crashes[J]. Transportation Research Part C,2012,24:288-298. [ 9 ] LIN L,WANG Q,SADEK A W.A Novel Variable Selection Method Based on Frequent Pattern Tree for Realtime Traffic Accident Risk Prediction[J].Transportation Research Part C,2015,55:444-459. [10] HOSSAIN M,MUROMACHI Y.A Bayesian Network Based Framework for Real-time Crash Prediction on the Basic Freeway Segments of Urban Expressways[J]. Accident Analysis and Prevention,2012,45:373-381. [11] YU R,ABDEL-ATY M.Utilizing Support Vector Machine in Real-time Crash Risk Evaluation[J].Accident Analysis and Prevention,2013,51:252-259. [12] WU M,SHAN D,WANG Z,et al.A Bayesian Network Model for Real-time Crash Prediction Based on Selected Variables by Random Forest[C]//The 5th International Conference on Transportation Information and Safety (ICTIS 2019).Piscataway:IEEE,2019. [13] 樊博,马筱栎,雷小诗,等.基于支持向量机的高速公路事故实时风险预测[J].工业工程,2021,24(4):143-149. [14] YOU J,WANG J,GUO J.Real-time Crash Prediction on Freeways Using Data Mining and Emerging Techniques[J].Modern Transportation,2017,25(2):116-123. [15] ABDEL-ATY M,PANDE A.Identifying Crash Propensity Using Specific Traffic Speed Conditions[J].Journal of Safety Research,2005,36:97-108. [16] OH C,OH J,RITCHIE S,et al.Real-time Hazardous Traffic Condition Warning System:Framework and Evaluation[J].IEEE Transactions on Intelligent Transportation Systems,2005,6(3):265-272. [17] 高昆.基于交通流的实时交通状态辨识及事故风险预警模型研究[D].西安:长安大学,2019. [18] 赵海涛,程慧玲,丁仪,等.基于深度学习的车联边缘网络交通事故风险预测算法研究[J].电子与信息学报, 2020,42(1):50-57. [19] 包杰.基于多源数据的城市路网交通事故风险研究 [D].南京:东南大学,2019. [20] 袁振洲,胡嫣然,杨洋.考虑多维动态特征交互的高速公路实时事故风险建模[J].交通运输系统工程与信息,2022,22(3):215-223. [21] LI P,ABDEL-ATY M,YUAN J.Real-time Crash Risk Prediction on Arterials Based on LSTM-CNN[J]. Accident Analysis and Prevention,2020,135:105371. [22] MAN C K,QUDDUS M,Theofilatos A.Transfer Learning for Spatio-temporal Transferability of Real-time Crash Prediction Models[J].Accident Analysis and Prevention,2022,165:106511. [23] YUAN J,ABDEL-ATY M,GONG Y,et al.Real-time Crash Risk Prediction Using Long Short-term Memory Recurrent Neural Network[J].Transportation Research Record,2019(4):314-326. [24] ZHANG S,ABDEL-ATY M.Real-time Crash Potential Prediction on Freeways Using Connected Vehicle Data[J].Analytic Methods in Accident Research,2022,36: 100239. [25] 于翔海,白佃国,于光,等.基于 XGBoost 模型的城市道路实时交通事故风险预测研究[J].公路交通科技, 2023,40(4):237-247. [26] HU Z,ZHOU J,HUANG K,et al.A Data-driven Approach for Traffic Crash Prediction:A Case Study in Ningbo, China[J].International Journal of Intelligent Transportation Systems Research,2022,20(2):508-518.