基于支持向量机的高速公路事故实时风险预测

doi:10.3969/j.issn.1007-7375.2021.04.017

工业工程 ›› 2021, Vol. 24 ›› Issue (4): 143-149.doi: 10.3969/j.issn.1007-7375.2021.04.017

基于支持向量机的高速公路事故实时风险预测

樊博, 马筱栎, 雷小诗, 马新露

重庆交通大学交通运输学院，重庆 400074

收稿日期:2020-04-22 发布日期:2021-09-02
通讯作者: 马新露(1981-)，男，重庆市人，教授，博士，主要研究方向为智能交通运输。E-mail：mxl2002@163.com E-mail:mxl2002@163.com
作者简介:樊博(1994-)，男，四川省人，硕士研究生，主要研究方向为智能交通运输
基金资助:
重庆市科技局资助项目(cstc2018jscx-mszdX0112)

Real-time Accident Risk Prediction on Freeway Based on Support Vector Machine

FAN Bo, MA Xiaoli, LEI Xiaoshi, MA Xinlu

College of Traffic and Transportation, Chongqing Jiaotong University, Chongqing 400074, China

Received:2020-04-22 Published:2021-09-02

摘要/Abstract

摘要： 以高速公路事故数据、交通流数据和天气数据为基础，以交通流为事故主要影响因素，建模预测高速公路事故实时风险。将事故记录作为病例组，采用病例对照方法来配对匹配实验样本，通过随机森林算法从众多变量中筛选出对事故风险影响最重要的10 个特征变量，以支持向量机建立模型预测事故实时风险。实验表明，通过随机森林筛选重要的特征变量，再使用支持向量机建模预测事故风险具有可行性，且以高斯核、Sigmoid核作为支持向量机的核函数比线性核函数和多项式核函数时分类准确性更高；其中，高斯核下支持向量机模型对事故风险预判的准确率达73.20%，对正常交通流的分类达91.44%。

关键词: 交通工程, 事故风险, 支持向量机, 病例-对照研究, 随机森林

Abstract: Based on the freeway accident data, traffic data, and weather data, a model is built to predict the real-time accident risk by taking traffic flow as the main influencing factor of accidents. Firstly, regarding each accident in the records as a case and the experimental case group is obtained, and then by the case-control study method, the matched corresponding control group set up. Then the random forest algorithm is used to screen out the 10 most important variables impacting the accident risk most. Finally, a model is built to predict real-time accident risk based on the support vector machine. Experiments show the SVM model we built works when predicting the accident risk. At the same time, the SVM model performance with the Gaussian and Sigmoid kernel is better than with the linear and polynomial kernel. Experiments showed the SVM model we built works when predicting the accident risk. At the same time, the SVM model performance with the Gaussian or Sigmoid kernel is better than with the linear or polynomial kernel. Especially the accuracy of the SVM model with the Gaussian kernel reaches 73.20% and 91.44% respectively when predicting the accident and non-accident situation.

Key words: traffic engineering, accident risk, support vector machine, case-control study, random forest

中图分类号:

U492.8

樊博, 马筱栎, 雷小诗, 马新露. 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.

FAN Bo, MA Xiaoli, LEI Xiaoshi, MA Xinlu. Real-time Accident Risk Prediction on Freeway Based on Support Vector Machine[J]. Industrial Engineering Journal, 2021, 24(4): 143-149.

参考文献

[1] ABDEL-ATY M, PANDE A, LEE C, et al. Crash risk assessment using intelligent transportation systems data and real-time intervention strategies to improve safety on freeways[J]. Journal of Intelligent Transportation Systems, 2007, 11(3): 107-120
[2] XU C, LIU P, WANG W, et al. Evaluation of the impacts of traffic states on crash risks on freeways[J]. Accident Analysis & Prevention, 2012, 47(1): 162-171
[3] 孙剑, 孙杰. 城市快速路实时交通流运行安全主动风险评估[J]. 同济大学学报(自然科学版), 2014, 42(6): 873-879
SUN Jian, SUN Jie. Proactive assessment of real-time traffic flow accident risk on urban expressway[J]. Journal of Tongji University (Natural Science), 2014, 42(6): 873-879
[4] YU R, WANG X, YANG K, et al. Crash risk analysis for Shanghai urban expressways: a Bayesian semi-parametric modeling approach[J]. Accident Analysis & Prevention, 2016, 95(1): 492-502
[5] LI P, ABDEL-ATY M, YUAN J. Real-time crash risk prediction on arterials based on LSTM-CNN[J]. Accident Analysis & Prevention, 2020, 135(1): 1-9
[6] 马壮林, 邵春福, 胡大伟, 等. 高速公路交通事故起数时空分析模型[J]. 交通运输工程学报, 2012, 12(2): 93-99
MA Zhuanglin, SHAO Chunfu, HU Dawei, et al. Temporal-spatial analysis model of traffic accident frequency on expressway[J]. Journal of Traffic and Transportation Engineering, 2012, 12(2): 93-99
[7] 孟祥海, 张晓明, 郑来. 基于线形与交通状态的山区高速公路追尾事故预测[J]. 中国公路学报, 2012, 43(4): 113-118
MENG Xianghai, ZHANG Xiaoming, ZHENG Lai. Prediction of rear-end collision on mountainous expressway based on geometric a lignment and traffic conditions[J]. China Journal of Highway and Transport, 2012, 43(4): 113-118
[8] 由冰玉, 廉福绵, 孟祥海. 基于故障树贝叶斯网的山区高速公路事故成因分析[J]. 交通信息与安全, 2019, 37(4): 44-51
YOU Bingyu, LIAN Fumian, MENG Xianghai. An analysis of crash factors for freeways in mountain areas based on fault tree and bayesian network[J]. Journal of Transport Information and Safety, 2019, 37(4): 44-51
[9] 马壮林, 张宏璐, 张祎祎, 等. 高速公路路侧事故起数预测模型[J]. 长安大学学报 (自然科学版), 2017, 37(4): 119-126
MA Zhuanglin, ZHANG Honglu, ZHANG Yiyi, et al. Roadside accident frequency prediction model on expressway[J]. Journal of Chang'an University (Natural Science Edition), 2017, 37(4): 119-126
[10] 马聪, 张生瑞, 马壮林, 等. 高速公路交通事故非线性负二项预测模型[J]. 中国公路学报, 2018, 31(11): 176-185
MA Cong, ZHANG Shengrui, MA Zhuanglin, et al. Nonlinear negative binomial regression model of expressway traffic accident frequency prediction[J]. China Journal of Highway and Transport, 2018, 31(11): 176-185
[11] 吴佩洁, 孟祥海, 崔洪海. 面向 NSM 的高速公路大区段事故风险预测方法[J]. 交通信息与安全, 2018, 36(4): 13-20
WU Peijie, MENG Xianghai, CUI Honghai. A crash prediction method for long segments on freeways based on road network traffic safety management[J]. Journal of Transport Information and Safety, 2018, 36(4): 13-20
[12] JUNG S, QIN X, NOYCE D A. Rainfall effect on single-vehicle crash severities using polychotomous response models[J]. Accident Analysis & Prevention, 2010, 42(1): 213-224
[13] 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
XU Chengcheng, LIU Pan, WANG Wei, et al. Realtime crash risk prediction model on freeways under nasty weather conditions[J]. Journal of Jilin University (Engineering and Technology Edition), 2013, 43(1): 68-73
[14] XU C, LIU Pan, WANG Wei. Evaluation of the predictability of real-time crash risk models[J]. Accident Analysis & Prevention, 2016, 94(1): 207-215
[15] 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(1): 9-19

基于支持向量机的高速公路事故实时风险预测

Real-time Accident Risk Prediction on Freeway Based on Support Vector Machine

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李丹, 朱宗乾, 贾义伍. 中小企业SaaS ERP采纳价值-风险模型研究[J]. 工业工程, 2020, 23(6): 42-51.
[2]	李莉, 何曙光. 基于LSSVM的多元过程非参数监控方法研究[J]. 工业工程, 2020, 23(1): 18-22,34.
[3]	王海燕, 侯琳娜. 基于随机森林的统计控制图模式识别研究[J]. 工业工程, 2019, 22(5): 118-125.
[4]	曹涛涛, 蒋阳升, 赵斌, 姚志洪, 谭宇. 考虑多交叉口相互影响的干道相位差仿真优化研究[J]. 工业工程, 2018, 21(6): 40-45.
[5]	王逸, 姚志洪, 蒋阳升, 赵斌, 谭宇. 基于自适应遗传算法的双环信号配时优化模型[J]. 工业工程, 2018, 21(5): 72-80.
[6]	李彦瑾, 罗霞, 王莹. 考虑多节点拥堵的城市道路网级联失效仿真[J]. 工业工程, 2018, 21(4): 1-7.
[7]	姚志洪, 蒋阳升, 王逸. 车路协同环境下自适应信号配时优化模型[J]. 工业工程, 2018, 21(4): 8-14,33.
[8]	殷旅江1，2，杨立君1, 何波1. 基于主成分分析与支持向量机的汽柴油需求预测[J]. 工业工程, 2015, 18(2): 20-27.
[9]	钟映竑，黄鑫. 基于粗糙集和支持向量机理论的物流需求预测研究[J]. 工业工程, 2015, 18(2): 28-33.
[10]	高妮妮1，刘子先2, 张海英3. 基于CV-SVM方法的手术时间估计[J]. 工业工程, 2014, 17(4): 111-115.
[11]	王宇凡，张淑娟, 梁工谦. 非线性复合FSVM在设备故障诊断中的应用[J]. 工业工程, 2014, 17(4): 139-144.
[12]	颜瑞，张群. 基于改进免疫算法优化支持向量机的钢材消费预测[J]. 工业工程, 2013, 16(5): 90-95.
[13]	张敏，程文明. 基于自适应粒子群算法和支持向量机的控制图模式识别[J]. 工业工程, 2012, 15(5): 125-129.
[14]	倪渊1，林健2. 基于Choquet模糊积分SVM集成及其实证研究[J]. 工业工程, 2012, 15(2): 66-70.
[15]	宋晓东，韩立岩. 基于双隶属模糊支持向量机的中小企业信用评价[J]. 工业工程, 2012, 15(1): 93-98.