Accident prediction model fusing heterogeneous traffic situations

doi:10.11772/j.issn.1001-9081.2022101619

Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (11): 3625-3631.DOI: 10.11772/j.issn.1001-9081.2022101619

Special Issue: 前沿与综合应用

• Frontier and comprehensive applications • Previous Articles Next Articles

Accident prediction model fusing heterogeneous traffic situations

Bo YANG, Zongtao DUAN(), Pengfei ZUO, Yuanyuan XIAO, Yilin WANG

School of Information Engineering，Chang’an University，Xi’an Shaanxi 710064，China

Received:2022-10-28 Revised:2023-04-05 Accepted:2023-08-07 Online:2023-05-24 Published:2023-11-10
Contact: Zongtao DUAN
About author:YANG Bo， born in 1999， M. S. candidate. His research interests include big data， deep learning.
DUAN Zongtao， born in 1977， Ph. D.， professor. His research interests include big data intelligence， analysis of big traffic data.
ZUO Pengfei， born in 1997， M. S. candidate. Her research interests include machine learning， analysis of big traffic data.
XIAO Yuanyuan， born in 1997， Ph. D. candidate. Her research interests include machine learning， data mining.
WANG Yilin， born in 1999， M. S. candidate. Her research interests include data clustering， user portrait.
Supported by:
Key Research and Development Program of Shaanxi Province(2019ZDLGY17-08);Project of “Special Support Plan” Science and Technology Innovation Leading Talents of Shaanxi Province(TZ0336)

融合异构交通态势的事故预测模型

杨博, 段宗涛(), 左鹏飞, 肖媛媛, 王艺霖

长安大学信息工程学院，西安 710064

通讯作者: 段宗涛
作者简介:杨博（1999—），男，山西运城人，硕士研究生，CCF会员，主要研究方向：大数据、深度学习
段宗涛（1977—），男，陕西凤翔人，教授，博士，CCF会员，主要研究方向：大数据智能、交通大数据分析 ztduan@chd.edu.cn
左鹏飞（1997—），女，山西大同人，硕士研究生，主要研究方向：机器学习、交通大数据分析
肖媛媛（1997—），女，陕西西安人，博士研究生，主要研究方向：机器学习、数据挖掘
王艺霖（1999—），女，山西太原人，硕士研究生，主要研究方向：数据聚类、用户画像。
基金资助:
陕西省重点研发计划项目(2019ZDLGY17?08);陕西省“特支计划”科技创新领军人才项目(TZ0336)

Abstract

Abstract:

To address the problems of limited information expression， imbalance， and dynamic spatio-temporal characteristics of accident data， an accident prediction model fusing heterogeneous traffic situations was proposed. In which， the semantic enhancement was completed by the spatio-temporal state aggregation module through traffic events and weather features representing dynamic traffic situations， and the historical multi-period spatio-temporal states of four types of regions （single region， adjacent region， similar region， and global region） were aggregated； the dynamic local and global spatio-temporal characteristics of accident data were captured by the spatio-temporal relation capture module from both micro- and macro-perspectives； and the multi-region and multi-angle spatio-temporal states were further fused by the spatio-temporal data fusion module， and the accident prediction task in the next period was realized. Experimental results on five city datasets of US-Accident demonstrate that the average F1-scores of the proposed model for accident， non-accident， and weighted average samples are 85.6%， 86.4%， and 86.6% respectively， which are improved by 14.4%， 5.6%， and 9.3% in the three metrics compared to the traditional Feedforward Neural Network （FNN）， indicating that the proposed model can effectively suppresses the influence of accident data imbalance on experimental results. Constructing an efficient accident prediction model helps to analyze the safety situation of road traffic， reduce the occurrence of traffic accidents and improve the traffic safety.

Key words: traffic accident prediction model, traffic accident data, spatio-temporal characteristic, deep learning, traffic safety

摘要：

针对事故数据信息表达有限、数据不平衡以及数据中存在动态时空特性的问题，提出一种融合异构交通态势的事故预测模型。其中：时空状态聚合模块通过代表动态交通态势的交通事件和天气特征完成语义增强，并聚合四种区域（单一区域、邻近区域、相似区域和全局区域）的历史多时段时空状态；时空关系捕获模块从微观和宏观角度捕获事故数据局部与全局的动态时空特性；时空数据融合模块进一步融合多区域、多角度的时空状态，并完成下一时段的事故状况预测任务。在US-Accident的5个城市数据集上进行实验，结果表明所提模型的正样本、负样本、加权正负样本的平均F1分数分别为85.6%、86.4%和86.6%，与传统的前馈神经网络（FNN）模型相比，在三个指标上分别提升了14.4%、5.6%和9.3%，能有效抑制事故数据不平衡对实验结果的影响。构建高效的事故预测模型有助于分析道路交通安全形势，减少交通事故的发生，提高交通安全。

关键词: 交通事故预测模型, 交通事故数据, 时空特性, 深度学习, 交通安全

CLC Number:

TP391

Bo YANG, Zongtao DUAN, Pengfei ZUO, Yuanyuan XIAO, Yilin WANG. Accident prediction model fusing heterogeneous traffic situations[J]. Journal of Computer Applications, 2023, 43(11): 3625-3631.

杨博, 段宗涛, 左鹏飞, 肖媛媛, 王艺霖. 融合异构交通态势的事故预测模型[J]. 《计算机应用》唯一官方网站, 2023, 43(11): 3625-3631.

Figures/Tables 8

References 25

1	SILVA P B， ANDRADE M， FERREIRA S. Machine learning applied to road safety modeling： a systematic literature review［J］. Journal of Traffic and Transportation Engineering （English Edition）， 2020， 7（6）： 775-790. 10.1016/j.jtte.2020.07.004
2	REN H， SONG Y， WANG J， et al. A deep learning approach to the citywide traffic accident risk prediction［C］// Proceedings of the 21st International Conference on Intelligent Transportation Systems. Piscataway： IEEE， 2018：3346-3351. 10.1109/itsc.2018.8569437
3	ZIAKOPOULOS A， YANNIS G. A review of spatial approaches in road safety［J］. Accident Analysis and Prevention， 2020， 135： No.105323. 10.1016/j.aap.2019.105323
4	JIANG W， LUO J. Graph neural network for traffic forecasting： a survey［J］. Expert Systems with Applications， 2022， 207： No.117921. 10.1016/j.eswa.2022.117921
5	HAMAMI M AL， MATISZIW T C. Measuring the spatiotemporal evolution of accident hot spots［J］. Accident Analysis and Prevention， 2021， 157： No.106133. 10.1016/j.aap.2021.106133
6	YU H， YUAN R， LI Z， et al. Identifying heterogeneous factors for driver injury severity variations in snow-related rural single-vehicle crashes［J］. Accident Analysis and Prevention， 2020， 144： No.105587. 10.1016/j.aap.2020.105587
7	ABELLÁN J， LÓPEZ G， DE OÑA J. Analysis of traffic accident severity using Decision Rules via Decision Trees［J］. Expert Systems with Applications， 2013， 40（15）： 6047-6054. 10.1016/j.eswa.2013.05.027
8	ALOGAILI A， MANNERING F. Unobserved heterogeneity and the effects of driver nationality on crash injury severities in Saudi Arabia［J］. Accident Analysis and Prevention， 2020， 144： No.105618. 10.1016/j.aap.2020.105618
9	CHANG L Y， CHEN W C. Data mining of tree-based models to analyze freeway accident frequency［J］. Journal of Safety Research， 2005， 36（4）： 365-375. 10.1016/j.jsr.2005.06.013
10	LV Y， TANG S， ZHAO H. Real-Time highway traffic accident prediction based on the k-nearest neighbor method［C］// Proceedings of the 2009 International Conference on Measuring Technology and Mechatronics Automation. Piscataway： IEEE， 2009： 547-550. 10.1109/icmtma.2009.657
11	TEDJOPURNOMO D A， BAO Z， ZHENG B， et al. A survey on modern deep neural network for traffic prediction： trends， methods and challenges［J］. IEEE Transactions on Knowledge and Data Engineering， 2022， 34（4）： 1544-1561.
12	MOOSAVI S， SAMAVATIAN M H， PARTHASARATHY S， et al. Accident risk prediction based on heterogeneous sparse data： new dataset and insights［C］// Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. New York： ACM， 2019：33-42. 10.1145/3347146.3359078
13	YUAN Z， ZHOU X， YANG T. Hetero-ConvLSTM： a deep learning approach to traffic accident prediction on heterogeneous spatio-temporal data［C］// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2018： 984-992. 10.1145/3219819.3219922
14	HAMILTON W. 图表示学习［M］. AI TIME，译. 北京：电子工业出版社， 2021： 72-113. 10.1007/978-3-031-01588-5_9
	HAMILTON W. Graph Representation Learning［M］. AI TIME， translated. Beijing： Publishing House of Electronics Industry， 2021： 72-113. 10.1007/978-3-031-01588-5_9
15	ZHOU Z， WANG Y， XIE X， et al. RiskOracle： a minute-level citywide traffic accident forecasting framework［C］// Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2020： 1258-1265. 10.1609/aaai.v34i01.5480
16	YU L， DU B， HU X， et al. Deep spatio-temporal graph convolutional network for traffic accident prediction［J］. Neurocomputing， 2021， 423： 135-147. 10.1016/j.neucom.2020.09.043
17	CHEN Q， SONG X， YAMADA H S， et al. Learning deep representation from big and heterogeneous data for traffic accident inference［C］// Proceedings of the 30th AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2016：338-344. 10.1609/aaai.v30i1.10011
18	YUAN Z， ZHOU X， YANG T， et al. Predicting traffic accidents through heterogeneous urban data： a case study［C］// Proceedings of the 6th International Workshop on Urban Computing. New York： ACM， 2017：1-9.
19	LOBO A， FERREIRA S， IGLESIAS I， et al. Urban road crashes and weather conditions： untangling the effects［J］. Sustainability， 2019， 11（11）： No.3176. 10.3390/su11113176
20	MALIN F， NORROS I， INNAMAA S. Accident risk of road and weather conditions on different road types［J］. Accident Analysis and Prevention， 2019， 122： 181-188. 10.1016/j.aap.2018.10.014
21	ROLAND J， WAY P D， FIRAT C， et al. Modeling and predicting vehicle accident occurrence in Chattanooga， Tennessee［J］. Accident Analysis and Prevention， 2021， 149： No.105860. 10.1016/j.aap.2020.105860
22	TAN P N， STEINBACH M， KUMAR V. 数据挖掘导论（完整版）［M］. 范明，范宏建，译.北京：人民邮电出版社， 2011： 180-186.
	TAN P N， STEINBACH M， KUMAR V. Introduction to Data Mining［M］. FAN M， FAN H J， translated. Beijing： Posts and Telecom Press， 2011： 180-186.
23	WALKER S H， DUNCAN D B. Estimation of the probability of an event as a function of several independent variables［J］. Biometrika， 1967， 54（1/2）： 167-179. 10.1093/biomet/54.1-2.167
24	BREIMAN L. Random forests［J］. Machine Learning， 2001， 45（1）： 5-32. 10.1023/a:1010933404324
25	PEDREGOSA F， VAROQUAUX G， GRAMFORT A， et al. Scikit-learn： machine learning in Python［J］. Journal of Machine Learning Research， 2011， 12： 2825-2830.

城市	网格大小	事故时段数	非事故时段数	交通事件数	POI数
Atlanta	9×8	2 446	147 698	43 228	16 393
Austin	12×13	4 055	282 985	46 822	21 745
Charlotte	11×12	4 945	246 800	52 988	18 718
Dallas	15×13	3 252	358 860	70 843	39 041
Houston	19×15	5 581	544 211	87 929	60 808

城市	网格大小	事故时段数	非事故时段数	交通事件数	POI数
Atlanta	9×8	2 446	147 698	43 228	16 393
Austin	12×13	4 055	282 985	46 822	21 745
Charlotte	11×12	4 945	246 800	52 988	18 718
Dallas	15×13	3 252	358 860	70 843	39 041
Houston	19×15	5 581	544 211	87 929	60 808

模型	Atlanta			Austin			Charlote			Dallas			Houston
模型	Acc	Non-Acc	Avg-Acc	Acc	Non-Acc	Avg-Acc	Acc	Non-Acc	Avg-Acc	Acc	Non-Acc	Avg-Acc	Acc	Non-Acc	Avg-Acc
LR	0.77	0.77	0.77	0.79	0.83	0.81	0.76	0.78	0.77	0.67	0.81	0.76	0.76	0.85	0.82
RF	0.77	0.77	0.77	0.80	0.84	0.82	0.79	0.77	0.78	0.63	0.85	0.78	0.73	0.86	0.81
FNN	0.76	0.77	0.76	0.79	0.83	0.81	0.78	0.79	0.79	0.65	0.84	0.78	0.76	0.86	0.82
SSAG	0.81	0.75	0.78	0.79	0.79	0.79	0.81	0.75	0.78	0.69	0.82	0.78	0.78	0.85	0.82
AP-FHTS	0.85	0.81	0.83	0.86	0.86	0.86	0.87	0.84	0.86	0.84	0.91	0.89	0.86	0.90	0.89

模型	Atlanta			Austin			Charlote			Dallas			Houston
模型	Acc	Non-Acc	Avg-Acc	Acc	Non-Acc	Avg-Acc	Acc	Non-Acc	Avg-Acc	Acc	Non-Acc	Avg-Acc	Acc	Non-Acc	Avg-Acc
LR	0.77	0.77	0.77	0.79	0.83	0.81	0.76	0.78	0.77	0.67	0.81	0.76	0.76	0.85	0.82
RF	0.77	0.77	0.77	0.80	0.84	0.82	0.79	0.77	0.78	0.63	0.85	0.78	0.73	0.86	0.81
FNN	0.76	0.77	0.76	0.79	0.83	0.81	0.78	0.79	0.79	0.65	0.84	0.78	0.76	0.86	0.82
SSAG	0.81	0.75	0.78	0.79	0.79	0.79	0.81	0.75	0.78	0.69	0.82	0.78	0.78	0.85	0.82
AP-FHTS	0.85	0.81	0.83	0.86	0.86	0.86	0.87	0.84	0.86	0.84	0.91	0.89	0.86	0.90	0.89

[1]	Yexin PAN, Zhe YANG. Optimization model for small object detection based on multi-level feature bidirectional fusion [J]. Journal of Computer Applications, 2024, 44(9): 2871-2877.
[2]	Yunchuan HUANG, Yongquan JIANG, Juntao HUANG, Yan YANG. Molecular toxicity prediction based on meta graph isomorphism network [J]. Journal of Computer Applications, 2024, 44(9): 2964-2969.
[3]	Jing QIN, Zhiguang QIN, Fali LI, Yueheng PENG. Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network [J]. Journal of Computer Applications, 2024, 44(9): 2970-2974.
[4]	Xiyuan WANG, Zhancheng ZHANG, Shaokang XU, Baocheng ZHANG, Xiaoqing LUO, Fuyuan HU. Unsupervised cross-domain transfer network for 3D/2D registration in surgical navigation [J]. Journal of Computer Applications, 2024, 44(9): 2911-2918.
[5]	Shunyong LI, Shiyi LI, Rui XU, Xingwang ZHAO. Incomplete multi-view clustering algorithm based on self-attention fusion [J]. Journal of Computer Applications, 2024, 44(9): 2696-2703.
[6]	Yuhan LIU, Genlin JI, Hongping ZHANG. Video pedestrian anomaly detection method based on skeleton graph and mixed attention [J]. Journal of Computer Applications, 2024, 44(8): 2551-2557.
[7]	Yanjie GU, Yingjun ZHANG, Xiaoqian LIU, Wei ZHOU, Wei SUN. Traffic flow forecasting via spatial-temporal multi-graph fusion [J]. Journal of Computer Applications, 2024, 44(8): 2618-2625.
[8]	Qianhong SHI, Yan YANG, Yongquan JIANG, Xiaocao OUYANG, Wubo FAN, Qiang CHEN, Tao JIANG, Yuan LI. Multi-granularity abrupt change fitting network for air quality prediction [J]. Journal of Computer Applications, 2024, 44(8): 2643-2650.
[9]	Zheng WU, Zhiyou CHENG, Zhentian WANG, Chuanjian WANG, Sheng WANG, Hui XU. Deep learning-based classification of head movement amplitude during patient anaesthesia resuscitation [J]. Journal of Computer Applications, 2024, 44(7): 2258-2263.
[10]	Huanhuan LI, Tianqiang HUANG, Xuemei DING, Haifeng LUO, Liqing HUANG. Public traffic demand prediction based on multi-scale spatial-temporal graph convolutional network [J]. Journal of Computer Applications, 2024, 44(7): 2065-2072.
[11]	Zhi ZHANG, Xin LI, Naifu YE, Kaixi HU. DKP： defending against model stealing attacks based on dark knowledge protection [J]. Journal of Computer Applications, 2024, 44(7): 2080-2086.
[12]	Yiqun ZHAO, Zhiyu ZHANG, Xue DONG. Anisotropic travel time computation method based on dense residual connection physical information neural networks [J]. Journal of Computer Applications, 2024, 44(7): 2310-2318.
[13]	Song XU, Wenbo ZHANG, Yifan WANG. Lightweight video salient object detection network based on spatiotemporal information [J]. Journal of Computer Applications, 2024, 44(7): 2192-2199.
[14]	Xun SUN, Ruifeng FENG, Yanru CHEN. Monocular 3D object detection method integrating depth and instance segmentation [J]. Journal of Computer Applications, 2024, 44(7): 2208-2215.
[15]	Yaxing BING, Yangping WANG, Jiu YONG, Haomou BAI. Six degrees of freedom object pose estimation algorithm based on filter learning network [J]. Journal of Computer Applications, 2024, 44(6): 1920-1926.

Accident prediction model fusing heterogeneous traffic situations

融合异构交通态势的事故预测模型

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 25

Related Articles 15

Recommended Articles

Metrics