Identification of Accident Black Spots Based on Improved Network Kernel Density and Negative Binomial Regression

doi:10.12141/j.issn.1000-565X.220659

Abstract

Abstract:

The existing research on identifying black spots in traffic accidents is mostly based on accident frequency or accident rate, without considering the impact characteristics of traffic accidents on different locations. In order to comprehensively consider the differential effects of traffic accidents in different traffic environments and road network characteristics and to solve the zero inflation problem of zero values far exceeding the classical discrete distribution in traffic accident data, this paper proposed an improved network kernel density estimation method that considers the comprehensive importance of nodes, and identified urban traffic accident black spots based on the zero inflation negative binomial regression model. Firstly, in the topological road network, a comprehensive impact index of accidents was constructed by comprehensively considering the traffic environment and road conditions at the location of the accident, and the accident severity index was embedded into the traditional network kernel density estimation. By generating a smooth density surface on the road network, the spatial aggregation of point events was qualitatively reflected. On this basis, a discrimination model based on zero-inflated negative binomial regression was constructed to clarify the boundary range of accident-prone areas and quantitatively depict the spatial distribution characteristics of accident black spots at different severity levels. Finally, an example analysis was carried out for Huaqiangbei street in Shenzhen. The results show that the search efficiency indexes of the proposed method are all larger than those of the planar kernel density estimation method at the threshold levels of 70%, 80% and 90%. Furthermore, some non-road areas are no longer mistaken, and the accuracy of the model is 3.60%, 5.31% and 7.20% larger than those of the traditional network kernel density method respectively after considering the comprehensive importance of nodes.

Key words: urban traffic, traffic accident, black spot identification, network kernel density estimation, zero-inflated negative binomial regression

CLC Number:

U491.3

ZHUANG Yan, DONG Chunjiao, MI Xueyu, et al.. Identification of Accident Black Spots Based on Improved Network Kernel Density and Negative Binomial Regression[J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(1): 119-126.

Figures/Tables 9

Fig.1

Fig.2

Table 1

Fig.3

Fig.4

Fig.5

Fig.6

Table 2

Fig.7

References 17

1	公安部道路交通安全研究中心．中国大城市道路交通发展研究报告（2018）［M］．北京：人民交通出版社，2020.
2	林鹏飞，翁剑成，付宇，等．基于刷卡数据的轨道交通加权网络结构特征［J］．吉林大学学报（工学版），2020，50（3）：956-962.
	LIN Peng-fei， WENG Jian-cheng， FU Yu，et al ．Structure characteristics of rail transit weighted network based on smart card data［J］．Journal of Jilin University （Engineering and Technology Edition），2020，50（3）：956-962.
3	ACHU A L， AJU C D， SURESH V，et al ．Spatio-temporal analysis of road accident incidents and delineation of hotspots using geospatial tools in Thrissur District，Kerala，India［J］．KN-Journal of Cartography and Geographic Information，2019，69（4）：255-265.
4	BASSANI M， ROSSETTI L， CATANI L ．Spatial analysis of road crashes involving vulnerable road users in support of road safety management strategies［J］．Transportation Research Procedia，2020，45：394-401.
5	HARIRFOROUSH H， BELLALITE L ．A new integrated GIS-based analysis to detect hotspots：a case study of the city of Sherbrooke［J］．Accident Analysis & Prevention，2019，130：62-74.
6	刘伟，陈科全，田宗忠，等．基于密度熵的道路交通事故影响范围分区模型［J］．交通运输工程学报，2019，19（6）：163-170．
	LIU Wei， CHEN Ke-quan， TIAN Zong-zhong，et al ．Partition model of road traffic accident influence area based on density entropy［J］．Journal of Traffic and Transportation Engineering，2019，19（6）：163-170.
7	RIDOUT M， DEMÉTRIO C G B， HINDE J ．Models for count data with many zeros［C］∥ Proceedings of the XIXth international biometric conference．Cape Town，SA：International Biometric Society Invited Papers，1998，19：179-192.
8	马壮林，张宏璐，杨杨．高速公路追尾碰撞事故起数预测模型研究［J］．中国安全科学学报，2015，25（4）：58-62.
	MA Zhuang-lin， ZHANG Hong-lu， YANG Yang ．Research on rear-end collision frequency prediction on expressway［J］．China Safety Science Journal，2015，25（4）：58-62.
9	WENG J， GE Y E， HAN H ．Evaluation of shipping accident casualties using zero-inflated negative binomial regression technique［J］．The Journal of Navigation，2016，69（2）：433-448.
10	龙雪琴，周萌，赵欢，等．基于网络核密度的网约车上下客热点识别［J］．交通运输系统工程与信息，2021，21（3）：86-93.
	LONG Xue-qin， ZHOU Meng， ZHAO Huan，et al ．Passengers’hot spots identification of online car-hailing based on network kernel density［J］．Journal of Transportation Systems Engineering and Information Technology，2021，21（3）：86-93.
11	XIE Z， YAN J ．Kernel density estimation of traffic accidents in a network space［J］．Computers，Environment and Urban Systems，2008，32（5）：396-406.
12	OUNI F， BELLOUMI M. Spatio-temporal pattern of vulnerable road user’s collisions hot spots and related risk factors for injury severity in Tunisia［J］．Transportation Research Part F：Traffic Psychology and Behaviour，2018，56：477-495.
13	CHAMLING M， BERA B ．Likelihood of elephant death risk applying kernel density estimation model along the railway track within biodiversity hotspot of Bhutan-Bengal Himalayan Foothill［J］．Modeling Earth Systems and Environment，2020，6（4）：2565-2580.
14	陈英，袁华智，黄中祥，等．零截尾负二项模型在交叉口事故预测中的应用［J］．中国公路学报，2020，33（4）：146-154．
	CHEN Ying， YUAN Hua-zhi， HUANG Zhong-xiang，et al ．Modeling intersection traffic crashes using a zero-truncated negative binomial model［J］．China Journal of Highway and Transport，2020，33（4）：146-154.
15	张大明，符茂胜，郭慧，等．基于惩罚距离的混合模型分量数自动估计算法［J］．华南理工大学学报（自然科学版），2009，37（10）：101-107．
	ZHANG Da-ming， FU Mao-sheng， GUO Hui，et al ．Automatic estimation algorithm mixture model based on of component number of penalized distance［J］．Journal of South China University of Technology （Natural Science Edition），2009，37（10）：101-107.
16	刘尧．交通事故的时空热点分析鉴别以及致因因素探究［D］．杭州：浙江大学，2019.
17	陈金林．基于网络核密度估计城市路网事故黑点鉴别研究［D］．南京：东南大学，2015.

影响指标			分类描述及对应离散化取值
道路条件	节点	节点交叉口类型	三路交叉口（1）四路交叉口（2）环形交叉口（3）
	节点相连道路	路面状况	水泥（1）水泥+沥青（2）沥青（3）
		节点相连道路等级	支路（3）次干路（5）主干路（8）
		节点相连道路限速	0~20 km/h（1） 20~30 km/h（2） 30~40 km/h（3）
环境条件	交通环境	交通拥堵程度	0~2（1） 2~4（2） 4~6（3）

累计概率/%	有效搜索指数/%
	平面核密度估计		网络核密度估计
	未考虑节点综合影响度	考虑节点综合影响度	未考虑节点综合影响度	考虑节点综合影响度
90	38.624	39.526（+2.34）	38.143	39.515（+3.60）
80	37.061	38.932（+5.05）	37.997	40.013（+5.31）
70	36.321	38.945（+7.22）	36.513	39.142（+7.20）

[1]	YANG Yazao, WENG Tangzheng. Impact of Spatiotemporal Constraints on Active Travel [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(2): 113-123.
[2]	ZHAO Xiaomei, HAO Guoyu, NIU Xiaojing, et al.. Traffic Boundary Control Strategy Based on Macroscopic Fundamental Diagram Under Different Rainfall [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(1): 72-82.
[3]	HU Xinghua, CHEN Xinghui, WANG Ran, et al. Optimization Model of Bus Priority Control Considering Carbon Emissions with Stochastic Characteristics [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(10): 160-170.
[4]	XU Lunhui, YU Jiaxin, PEI Mingyang, et al. Repositioning Strategy for Ride-Hailing Vehicles Based on Geometric Road Network Structure and Reinforcement Learning [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(10): 99-109.
[5]	SHEN Yutong, LI Ming, CUI Zhiyong, et al. Study on the Multi-Period Allocation Method of Vehicle Resource in Hybrid Service Mode [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(10): 89-98.
[6]	WANG Hao, XIE Ning . Coordinated Optimization Model of Arterial Segmented Green Waves Considering the Efficiency of Tram Operation [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(1): 95-105.
[7]	ZHAO Jiandong, ZHU Dan, LIU Jiaxin. Metro Transfer Passenger Flow Prediction Based on STL-GRU [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(5): 22-31.
[8]	WU Jiaorong XIE Jinhong WANG Yuqin. The Profiling Method of Instability of Bus Route Operation and Its Application [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(2): 15-22.
[9]	CHEN Xiaohong, HU Fang . Interval Optimization Model of Signal Control at Intersection Based on Possibility Degree [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(10): 29-40.
[10]	WANG Xiaofei LIU Yong LI Siyu. Correlation Model of the Influence of Freeway Spatial Curvature Continuity Decline on Accident Frequency [J]. Journal of South China University of Technology(Natural Science Edition), 2021, 49(8): 26-34.
[11]	CHEN Jiqing, SHU Xiaoxiong, LAN Fengchong, et al. Construction of Autonomous Vehicles Test Scenarios with Typical Dangerous Accident Characteristics [J]. Journal of South China University of Technology (Natural Science Edition), 2021, 49(5): 1-8.
[12]	YU Lijun. Generalized System-Optimal Traffic Assignment with Link Capacity Constraints [J]. Journal of South China University of Technology(Natural Science Edition), 2021, 49(4): 140-148.
[13]	YAO Enjian LU Muyang LIU Yuhuan YUAN Ling. Electric Bus Area Driving Plan Preparation Considering Charging Constraints [J]. Journal of South China University of Technology(Natural Science Edition), 2019, 47(9): 68-73.
[14]	LIU Zhongbo ZHAO Xiaohui. A Dynamic Allocation and Guidance Model for Parking Spaces with Minimum Total Parking Costs#br# [J]. Journal of South China University of Technology(Natural Science Edition), 2018, 46(9): 92-98.
[15]	LU Kai LIN Maowei DENG Xingdong XU Guanghui XU Jianmin. A model of area dynamic allocation and guidance of parking space with the minimum total parking cost [J]. Journal of South China University of Technology(Natural Science Edition), 2018, 46(9): 82-91,98.