Study on Accident Risk Based on Driving Behavior and Traffic Operating Status

doi:10.12141/j.issn.1000-565X.210629

Abstract

Abstract:

Accurate identification of traffic accident risk and timely mastering the change of traffic crash risk are of great significance for proactive prevention and reduction of traffic accident. Most of the existing traffic crash identification studies are based on real-time and dynamic parameters such as traffic flow and traffic conflict. The application of risky driving behavior in traffic accident risk detection is limited by the constraints of previous data acquisition technologies. To more accurately identify the risk of road traffic crashes, this study introduced risky driving behavior and traffic operating status and other big data, and extracted sharp acceleration, deceleration, turns, merge into other lane, traffic volume, average speed, and congestion index as variables. And traffic accident identification models were constructed based on accident data. The traffic accident identification model was evaluated based on the logistic regression algorithm. On the one hand, the contribution of risky driving behavior in traffic accident identification was quantified; on the other hand, the trend of traffic accident occurrence probability before and after the accident was analyzed. The results show that the sensitivity and AUC values of the traffic accident identification model considering both traffic operation state and risky driving behavior are increased by 5.00% and 0.03, respectively. The false alarm rate and missing report rate are decreased by 1.78% and 5.00%, respectively, which shows better fitting effect of the model. In addition, before and after the occurrence of traffic accidents, the risk probability of traffic crashes shows an obvious trend of rise, which is the key period of traffic accident prevention and control. The measures should be taken in corresponding sections in time to curb the rising trend of traffic crash risk and avoid the occurrence of traffic crashes. This study can provide intuitive basis for traffic accident prevention, and active prevention and control.

Key words: freeway, traffic safety, accident risk detection, driving behavior, traffic operating state

CLC Number:

U491

GUO Miao, ZHAO Xiaohua, YAO Ying, et al. Study on Accident Risk Based on Driving Behavior and Traffic Operating Status[J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(9): 29-38.

Figures/Tables 14

Table 1

Table 2

Table 3

Fig.1

Fig.2

Fig.3

Fig.4

Table 4

Table 5

Fig.5

Table 6

Fig.6

Table 7

Fig.7

References 24

1	赵琳娜．城市道路交通事故特点及解决对策［J］．汽车与安全，2018（5）：68-70.
	ZHAO Lin-na ．Characteristics and countermeasures of urban road traffic crashes［J］．Auto & Safety，2018（5）：68-70.
2	WU K F， AGUERO-VALVERDE J， JOVANIS P P ．Using naturalistic driving data to explore the association between traffic safety-related events and crash risk at driver level［J］．Accident Analysis & Prevention，2014，72：210-218.
3	HUGHES R， COUNCIL F，On establishing relationship（s） between freeway safety and peak period operations：performance measurement and methodological considerations［C］//78th Annual Meeting of Transportation Research Board．Washington：［s.n.］，1999.
4	ABDEL-ATY M， UDDIN N， PANDE A，et al ．Predicting freeway crashes from loop detector data by matched case-control logistic regression［J］．Transportation Research Record Journal of the Transportation Research Board，2004，1897：88-95.
5	PANDE A， ABDEL-ATY M ．Assessment of freeway traffic parameters leading to lane-change related collisions［J］．Accident Analysis & Prevention，2006，38（5）：936-948.
6	徐铖铖，刘攀，王炜，等．基于判别分析的高速公路交通安全实时评价指标［J］．东南大学学报（自然科学版），2012，42（3）：555-559.
	XU Cheng-cheng， LIU Pan， WANG Wei，et al ．Discriminant analysis based method to develop real-time crash indicator for evaluating freeway safety［J］．Journal of Southeast University （Natural Science Edition），2012，42（3）：555-559.
7	SHI Q， ABDEL-ATY M ．Big data applications in real-time traffic operation and safety monitoring and improvement on urban expressways［J］．Transportation Research Part C：Emerging Technologies，2015，58：380-394.
8	朱顺应，蒋若曦，王红，等．机动车交通冲突技术研究综述［J］．中国公路学报，2020，33（2）：15-33.
	ZHU Shun-ying， JIANG Ruo-xi， WANG Hong，et al ．Review of research on traffic conflict techniques［J］．China Journal of Highway and Transport，2020，33（2）：15-33.
9	江周，张存保，夏银霞．基于交通冲突的高速公路实时安全状态评价研究［J］．中国安全科学学报，2014，24（9）：95-101.
	JIANG Zhou， ZHANG Cun-bao， XIA Yin-xia ．research on real-time traffic safety state evaluation of freeway based on number of traffic conflicts［J］．China Safety Science Journal，2014，24（9）：95-101.
10	JIANG R， ZHU S， WANG P，et al ．Insearch of the consequence severity of traffic conflict［J］．Journal of Advanced Transportation，2020，2020（1186）：1-15.
11	GUO Y， SAYED T， ESSA M ．Real-time conflict-based bayesian tobit models for safety evaluation of signalized intersections［J］．Accident Analysis & Prevention，2020，144：105660.
12	张鑫，张卫华，冯忠祥，等．基于交通冲突技术的城市快速路合流区交通安全评价［J］．安全与环境工程，2020，27（4）：174-179.
	ZHANG Xin， ZHANG Wei-hua， FENG Zhong-xiang，et al ．Traffic safety evaluation of expressway confluence area based on traffic conflict technology［J］．Safety and Environmental Engineering，2020，27（4）：174-179.
13	孙璐，李颜平，钱军，等．基于交通冲突技术的交织区交通安全评价［J］．中国安全科学学报，2013，23（1）：55-60.
	SUN Lu， LI Yan-ping， QIAN Jun，et al ．Evaluation of weaving sections with respect to traffic safety based on traffic conflict technique［J］．China Safety Science Journal，2013，23（1）：55-60.
14	朱顺应，邹禾，蒋若曦，等．高速公路施工区合流路段交通冲突模型［J］．哈尔滨工业大学学报，2020，52（9）：70-76.
	ZHU Shun-ying， ZOU He， JIANG Ruo-xi，et al ．Traffic conflict model for confluence section in highway construction area［J］．Journal of Harbin Institute of Technology，2020，52（9）：70-76.
15	楚文慧，吴超仲，张晖，等．驾驶行为安全性评价研究综述［J］．公路交通科技，2017，34（S2）：8-15.
	CHU Wen-hui， WU Chao-zhong， ZHANG Hui，et al ．A review of safety evaluation of driving behaviors［J］．Journal of Highway and Transportation Research and Development，2017，34（S2）：8-15.
16	BAGDADI O ．Assessing safety critical braking events in naturalistic driving studies［J］．Transportation Research Part F：Traffic Psychology and Behaviour，2013，16：117-126.
17	TOLEDO T， LOTAN T ．Invehicle data recorder for evaluation of driving behavior and safety［J］．Transportation Research Record：Journal of the Transportation Research Board，2006，1953：112-119.
18	WANG Jian-qiang， ZHENG Yang， LI Xiao-fei，et al ．Driving risk assessment using near-crash database through data mining of tree-based model［J］．Accident； analysis and prevention，2015，84：54-64.
19	王雪松，徐晓妍．基于自然驾驶数据的危险事件识别方法［J］．同济大学学报（自然科学版），2020，48（1）：51-59.
	WANG Xue-song， XU Xiao-yan ．Detection of safety-critical events based on naturalistic driving data［J］．Journal of Tongji University（Natural Science），2020，48（1）：51-59.
20	Mobile Quest ．China mobile internet annual report in 2017［EB/OL］．［2019-04-02］．.
21	Federal Highway Administration ．Travel time reliability-making it there on time，all the time ［EB/OL］．［2006-01-21］．.
22	YUAN J， ABDEL-ATY M， GONG Y，et al ．Real-time crash risk prediction using long short-term memory recurrent neural network［J］．Transp Res Rec，2019，2673：314-326.
23	CAI Q， ABDEL-ATY M， YUAN J，et al ．Real-time crash prediction on expressways using deep generative models［J］．Transp Res Part C Emerg Technol，2020，117：102697.
24	BASSO F， BASSO L J， BRAVO F，et al ．Real-time crash prediction in an urban expressway using disaggregated data［J］．Transp Res Part C Emerg Technol，2018，86：202-219.

数据类别	主要字段	时间精度	空间精度
风险驾驶行为数据	急加速	1 s	经纬度
	急减速
	急左转
	急右转
	急左并道
	急右并道
交通流数据	平均速度	10 min	路段
	拥堵指数	10 min
	交通流量	5 min
交通事故数据	发生与否	1 min	路段

变量	急加速频率/（次·车^-1·（10 min）^-1）	急减速频率/（次·车^-1·（10 min）^-1）	急左转频率/（次·车^-1·（10 min）^-1）	急右转频率/（次·车^-1·（10 min）^-1）	急左并道频率/（次·车^-1·（10 min）^-1）	急右并道频率/（次·车^-1·（10 min）^-1）	流量/（辆·（10 min）^-1）	平均速度/（km·h^-1）	拥堵指数
平均值	0.002 2	0.002 0	0.000 1	0.000 1	<0.000 1	<0.000 1	175.413 6	77.440 8	1.080 9
标准差	0.011 4	0.001 0	0.002 5	0.002 9	0.001 7	0.001 7	118.168 0	9.628 3	0.441 9
最小值	0.000 0	0.000 0	0.000 0	0.000 0	0.000 0	0.000 0	1.000 0	2.304 0	0.760 0
最大值	2.000 0	1.000 0	0.260 9	0.666 7	0.222 2	0.333 3	1 009.000 0	112.644 0	33.850 0

变量类型	自变量	事故数相关系数r^1）/显著性（双侧）
风险驾驶行为	急减速	0.611** / 0.000
	急加速	0.623** / 0.000
	急左转	0.542** / 0.000
	急右转	0.614** / 0.000
	急左并道	0.403** / 0.000
	急右并道	0.495** / 0.000
交通运行状态	交通流量	0.468** / 0.000
	平均速度	0.314** / 0.014
	拥堵指数	0.295* / 0.020

数据类型	原始数据集	测试集	原始训练集	平衡训练集
事故数	200	60	140	199 677
非事故数	285 254	85 577	199 677	199 677
总数	285 454	85 637	199 817	399 354

训练集	变量	急加速频率/（次·车^-1·（10 min）^-1）	急减速频率/（次·车^-1·（10 min）^-1）	急左转频率/（次·车^-1·（10 min）^-1）	急右转频率/（次·车^-1·（10 min）^-1）	急左并道频率/（次·车^-1·（10 min）^-1）	急右并道频率/（次·车^-1·（10 min）^-1）	流量/（辆·（10 min）^-1）	平均速度/（km·h^-1）	拥堵指数
原始训练集	平均值	0.002 2	0.002 1	0.000 1	0.000 1	<0.000 1	<0.000 1	175.402 6	77.450 4	1.081 1
	标准差	0.010 4	0.009 8	0.002 6	0.003 0	0.001 8	0.001 7	118.168 7	9.624 1	0.450 4
	最小值	0.000 0	0.000 0	0.000 0	0.000 0	0.000 0	0.000 0	1.000 0	2.376 0	0.760 0
	最大值	1.000 0	1.000 0	0.260 9	0.666 7	0.222 2	0.333 3	1 009.000 0	112.644	33.640 0
平衡训练集	平均值	0.005 0	0.010 8	0.000 3	0.000 1	0.000 2	<0.000 1	229.770 7	64.496 4	1.518 0
	标准差	0.014 5	0.022 5	0.002 6	0.002 3	0.002 1	0.001 2	112.575 3	21.260 1	1.062 0
	最小值	0.000 0	0.000 0	0.000 0	0.000 0	0.000 0	0.000 0	1.000 0	2.376 0	0.760 0
	最大值	1.000 0	1.000 0	0.260 9	0.666 7	0.222 2	0.333 3	1 009.000 0	112.644 0	33.640 0