| 793 | 2 | 34 |
| 下载次数 | 被引频次 | 阅读次数 |
高速公路交通事故风险预测对于实行动态交通安全管理至关重要。为探究影响高速公路交通事故风险的主要因素以及准确预测高速公路交通事故风险，提出了一种基于改进深度森林算法的高速公路交通事故风险预测模型。首先以高速公路交通事故数据、交通流数据、天气数据、道路条件和特殊时间段数据为基础，选取了能够表征高速公路交通事故风险的特征变量，并采用随机森林算法对特征变量的重要度进行了计算，筛选出对高速公路交通事故风险影响较大的重要特征变量，以解决后面计算过程中的维度灾难问题；然后运用基于决策树的LightGBM和XGBoost算法对深度森林模型的级联森林结构进行了改进；最后将改进深度森林算法应用于高速公路事故风险预测。结果表明：与现有的SVM、随机森林和深度森林算法相比，改进深度森林算法具有更优的预测性能，其预测准确率达到了88.84%，预测结果能为高速公路交通管理部门制定更为有效的安全管控措施提供决策支持。
Abstract：Highway traffic accident risk prediction is very important for dynamic traffic safety management. In order to explore the main factors affecting the highway traffic accident risk and accurately predict the highway traffic accident risk, a highway traffic accident risk prediction model based on improved deep forest algorithm is proposed. Firstly, based on expressway traffic accident data, traffic flow data, weather data, road conditions and special time period data, the characteristic variables that can represent highway traffic accident risk were selected. The random forest algorithm was used to calculate the importance of the characteristic variables, and screen out the important characteristic variables that have a greater impact on the highway traffic accident risk, and solve the dimensional disaster problem in the following calculation process. Then the cascade forest structure of the deep forest model was improved by using LightGBM and XGBoost algorithms based on decision tree. Finally, the improved deep forest algorithm was applied to highway accident risk prediction. The results show that compared with the existing SVM, random forest and deep forest algorithms, the improved deep forest algorithm has better prediction performance, and the accuracy rate reaches 88. 84%. The prediction results can provide decision support for the highway traffic management department to make more effective safety control measures.
[1] CASTRO M, PALETI R, BHAT C R. A spatial generalized ordered response model to examine highway crash injury severity[J]. Accident Analysis&Prevention, 2013, 52:188-203.
[2] MALIN F, NORROS I, INNAMAA S. Accident risk of road and weather conditions on different road types[J]. Accident Analysis&Prevention, 2019, 122:181-188.
[3] HARB R, YAN X, RADWAN E, et al. Exploring precrash maneuvers using classification trees and random forests[J].Accident Analysis&Prevention, 2009, 41(1):98-107.
[4] LAZZERINI B, PISTOLESI F. Profiling risk sensibility through association rules[J]. Expert Systems with Applications, 2013, 40(5):1484-1490.
[5] LORD D, MANNERING F. The statistical analysis of crashfrequency data:A review and assessment of methodological alternatives[J]. Transportation Research Part A:Policy and Practice, 2010, 44(5):291-305.
[6] MILTON J, MANNERING F. The relationship among highway geometrics, traffic-related elements and motor-vehicle accident frequencies[J]. Transportation, 1998, 25(4):395-413.
[7] MOUDON A V, LIN L, JIAO J, et al. The risk of pedestrian injury and fatality in collisions with motor vehicles, a social ecological study of state routes and city streets in King County,Washington[J]. Accident Analysis&Prevention, 2011, 43(1):11-24.
[8] AHMED M, ABDEL-ATY M. A data fusion framework for real-time risk assessment on freeways[J]. Transportation Research Part C:Emerging Technologies, 2013, 26:203-213.
[9] DEUBLEIN M, SCHUBERT M, ADEY B T. Prediction of road accidents:Comparison of two Bayesian methods[J].Structure and Infrastructure Engineering, 2014, 10(11):1394-1416.
[10]BAO J, LIU P, UKKUSURI S V. A spatiotemporal deep learning approach for citywide short-term crash risk prediction with multi-source data[J]. Accident Analysis&Prevention,2019, 122:239-254.
[11]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&Prevention, 2012, 45:373-381.
[12]KWAK H C, KHO S. Predicting crash risk and identifying crash precursors on Korean expressways using loop detector data[J]. Accident Analysis&Prevention, 2016, 88:9-19.
[13]ROSHANDEL S, ZHENG Z, WASHINGTON S. Impact of real-time traffic characteristics on freeway crash occurrence:Systematic review and meta-analysis[J]. Accident Analysis&Prevention, 2015, 79:198-211.
[14]BASSO F, BASSO L J, BRAVO F, et al. Real-time crash prediction in an urban expressway using disaggregated data[J].Transportation Research Part C:Emerging Technologies,2018, 86:202-219.
[15]阮鸿柱，黄小弟，王金宝，等.面向高速公路事故风险预测的深度学习方法[J].计算机技术与发展，2023, 33(11):189-195.RUAN H Z, HUANG X D, WANG J B, et al. A deep learning approach for highway accident risk prediction[J].Computer Technology and Development, 2023, 33(11):189-195.
[16]FANG S, XIE W, WANG J, et al. Utilizing the eigenvectors of freeway loop data spatiotemporal schematic for real time crash prediction[J]. Accident Analysis&Prevention, 2016, 94:59-64.
[17]周鑫宇.基于时空注意力图卷积网络的交通事故风险预测方法研究[D].重庆：重庆大学，2022.ZHOU X Y. Research on Traffic Accident Risk Prediction Method Based on Spatio-Temporal Attention Graph Convolution Network[D]. Chongqing:Chongqing University,2022.
[18]于帅.基于气象条件与交通流交互作用的高速公路事故风险分析及预测[D].北京：北京交通大学，2020.YU S. Analysis and Prediction of Expressway Accident Risk Based on the Interaction between Meteorological Conditions and Traffic Flow[D]. Beijing:Beijing Jiaotong University,2020.
[19]袁振洲，娄晨，杨洋.时间差异条件下的高速公路交通事故致因分析[J].北京交通大学学报，2021, 45(3):1-7.YUAN Z Z, LOU C, YANG Y. Analysis of highway traffic accidents causes under time differences[J]. Journal of Beijing Jiaotong University, 2021, 45(3):1-7.
[20]LIN L, WANG Q, SADEK A W. A novel variable selection method based on frequent pattern tree for real-time traffic accident risk prediction[J]. Transportation Research Part C:Emerging Technologies, 2015, 55:444-459.
[21]游锦明，方守恩，张兰芳，等.高速公路实时事故风险研判模型及可移植性[J].同济大学学报（自然科学版），2019, 47(3):347-352.YOU J M, FANG S E, ZHANG L F, et al. Real-time crash risk prediction models and transferability analysis on freeways[J]. Journal of Tongji University(Natural Science), 2019, 47(3):347-352.
[22]SUN J, SUN J. A dynamic Bayesian network model for realtime crash prediction using traffic speed conditions data[J].Transportation Research Part C:Emerging Technologies,2015, 54:176-186.
[23]RETALLACK A E, OSTENDORF B. Relationship between traffic volume and accident frequency at intersections[J].International Journal of Environmental Research and Public Health, 2020, 17(4):1393.
[24]Breiman L. Random Forests[J]. Machine Learning, 2001,45(1):5-32.
基本信息:
DOI：10.13578/j.cnki.issn.1671-1556.20240624
中图分类号:U491.31
引用信息:
[1]张浩.基于改进深度森林算法的高速公路交通事故风险预测[J].安全与环境工程,2024,31(06):91-99.DOI:10.13578/j.cnki.issn.1671-1556.20240624.
基金信息:
湖北省安全生产专项资金科技项目（SJZX20230904）