[1]张延孔,卢家品,张帅超,等.基于路网结构的城市交通事故短期风险预测方法[J].智能系统学报,2020,15(4):663-671.[doi:10.11992/tis.201910002]
 ZHANG Yankong,LU Jiapin,ZHANG Shuaichao,et al.A short-term risk prediction method for urban traffic accidents based on road network[J].CAAI Transactions on Intelligent Systems,2020,15(4):663-671.[doi:10.11992/tis.201910002]
点击复制

基于路网结构的城市交通事故短期风险预测方法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第15卷
期数:
2020年4期
页码:
663-671
栏目:
学术论文—智能系统
出版日期:
2020-07-05

文章信息/Info

Title:
A short-term risk prediction method for urban traffic accidents based on road network
作者:
张延孔1 卢家品1 张帅超2 姬晓鹏2 罗月童1 陈为2
1. 合肥工业大学 计算机与信息学院,安徽 合肥 230000;
2. 浙江大学 计算机科学与技术学院,浙江 杭州 310018
Author(s):
ZHANG Yankong1 LU Jiapin1 ZHANG Shuaichao2 JI Xiaopeng2 LUO Yuetong1 CHEN Wei2
1. School of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230000, China;
2. College of Computer Science and Technology, Zhejiang University, Hangzhou 310018, China
关键词:
图卷积交通事故事故模式多源数据风险预测路网结构长短期记忆网络智慧城市
Keywords:
GCNNtraffic accidentaccident modemulti-source datarisk forecastingroad network structureLSTMsmart city
分类号:
TP18
DOI:
10.11992/tis.201910002
摘要:
城市交通事故一般都发生在公共道路上,然而现有的交通事故风险预测算法都通过对预测区域进行规则网格化来确定预测空间单位,导致预测精度不高且实用价值较低。本文将道路路段作为预测单位,采用图卷积和长短期记忆网络,构建了一种基于路网结构的城市交通事故短期风险预测方法(traffic accidents risk prediction based on road network,TARPBRN)。该方法能对指定路段短期内的交通事故风险进行预测,从而可以有针对性地进行治理,减少交通事故的发生。本文使用杭州市西湖区的交通事故数据对模型进行了训练,并与4种常用的计量经济学模型和3种已有的深度学习预测算法进行了对比。实验结果证明本文算法在准确度、正确率和漏报率等方面都优于已有算法。
Abstract:
Urban traffic accidents usually occur on public roads. However, the existing traffic accident risk prediction algorithms determine the prediction space unit by regularizing grid of the prediction area, which leads to low prediction accuracy and low practicability. Taking road sections as the prediction unit, this paper constructs a short-term traffic accident risk prediction method based on road network structure (TARPBRN) by using graph convolution and long short-term memory network. This method can predict the traffic accident risk in a short period of the designated section, so as to carry out targeted governance and reduce the occurrence of traffic accidents. In this paper, traffic accident data from Xihu District, Hangzhou city are used to train the model, and four econometric models and three existing deep learning prediction algorithms are compared. The experimental results show that the proposed algorithm is superior to the existing ones in accuracy, precision and false negative rate (FNR).

参考文献/References:

[1] World Health Organization. Global status report on road safety 2015[R]. World Health Organization, 2015.
[2] ZHANG Guangnan, KELVIN KW Yau, CHEN Guanghan. Risk factors associated with traffic violations and accident severity in China[J]. Accident analysis & prevention, 2013, 59: 18-25.
[3] 敖曼, 翟润平. 气象条件对道路交通的影响分析[J]. 公路与汽运, 2011(2): 58-62
AO Man, ZHAI Runping. Analysis of the influence of meteorological conditions on road traffic[J]. Highways & automotive applications, 2011(2): 58-62
[4] NOLAND R B. Traffic Fatalities and Injuries: the effect of changes in infrastructure and other trends[J]. Accident analysis & prevention, 2003, 35: 599-611.
[5] LI Z, WANG W, LIU P, et al. Using geographically weighted roisson regression for county-level crash modeling in california[J]. Safety science, 2013, 58: 89-97.
[6] 秦利燕, 邵春福, 赵亮. 道路交通事故宏观预测模型[J]. 武汉理工大学学报: 交通科学与工程版, 2010, 34(1): 158-161
QIN Liyan, SHAO Chunfu, ZHAO Liang. Macro prediction model of road traffic accident based on neural network[J]. Journal of Wuhan University of Technology (transportation science & engineering edition), 2010, 34(1): 158-161
[7] 张辉, 陈柯羽. 高速公路减速波事故的前兆特征与概率模型[J]. 交通运输研究, 2017, 3(5): 26-32
ZHANG Hui, CHEN Keyu. Precursory characteristics and probability model of deceleration wave accidents on expressways[J]. Transportation research, 2017, 3(5): 26-32
[8] 王健, 卢锡凤. 基于聚类分析的高速公路事故黑点鉴别及成因分析研究[J]. 公路交通技术, 2016, 32(5): 114-119
WANG Jian, LU Xifeng. Identification and cause analysis of expressway accident black spots based on cluster analysis[J]. Highway traffic technology, 2016, 32(5): 114-119
[9] BAO J, LIU P, YU H, et al. Incorporating twitter-based human activity information in spatial analysis of crashes in urban areas[J]. Accident analysis & prevention, 2017, 106: 358-369.
[10] SINNOTT R O, YIN S. Accident black spot identification and verification through social media[C]// IEEE International Conference on Data Science & Data Intensive Systems. Sydney, Australia, 2015.
[11] 李娟, 邵春福. 基于BP神经网络的交通事故预测模型[J]. 交通与计算机, 2006, 24(2): 34-37
LI Juan, SHAO Chunfu. Traffic accident prediction model based on BP neural network[J]. Traffic and computer, 2006, 24(2): 34-37
[12] 张志豪, 杨文忠, 袁婷婷, 等. 基于LSTM神经网络模型的交通事故预测[J]. 计算机工程与应用, 2019, 55(14): 249-253
ZHANG Zhihao, YANG Wenzhong, YUAN Tingting, et al. Traffic accident prediction based on LSTM neural network model[J]. Computer engineering and applications, 2019, 55(14): 249-253
[13] 胡立伟, 张婷, 郭凤香. 基于灰色BP神经网络的道路交通事故车型分担率预测及其预防策略研究[J]. 武汉理工大学学报(交通科学与工程版), 2018, 42(3): 388-392
HU Liwei, ZHANG Ti, GUO Fengxiang. Traffic accident split rate of vehicle types prediction and prevention Strategies study based on gray BP neural network[J]. Journal of Wuhan university of technology (transportation science & engineering edition), 2018, 42(3): 388-392
[14] MA X, TAO Z, WANG Y, et al. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data[J]. Transportation research part C: emerging technologies, 2015, 54: 187-197.
[15] CHEN Quanjun. Learning deep representation from big and heterogeneous data for traffic accident inference[C]//Thirtieth AAAI Conference on Artificial Intelligence. Phoenix, Arizona, United States, 2016: 338-344.
[16] REN Honglei. A deep learning approach to the citywide traffic accident risk prediction[C]// 2018 21st International Conference on Intelligent Transportation Systems (ITSC). Maui, United States, 2018: 3346-3351.
[17] 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.
[18] DEFFERRARD Micha?l, XAVIER Bresson, PIERRE rgheynst. Convolutional neural networks on graphs with fast localized spectral filtering[J]. Advances in neural information processing systems, 2016: 3844-3852.
[19] KIPF T N, MAX W. Semi-supervised classification with graph convolutional network[J]. arXiv preprint arXiv: 1609.02907, 2016.
[20] LIN Lei, HE Zhengbing, SRINIVAS Peeta. Predicting station-level hourly demand in a large-scale bike-sharing network: A graph convolutional neural network approach[J]. Transportation research part C: emerging technologies, 2018, 97: 258-276.
[21] GEORGE E P, DAVID A. Pierce. Distribution of residual autocorrelations in autoregressive-integrated moving average time series models[J]. Journal of the american statistical association, 1970, 65: 1509-1526.
[22] NAZNIN F. Application of a random effects negative binomial model to examine tram-involved crash frequency on route sections in Melbourne, Australia[J]. Accident analysis & prevention, 2016, 92: 15-21.
[23] BAO Jie. Incorporating twitter-based human activity information in spatial analysis of crashes in urban areas[J]. Accident analysis & prevention, 2017, 106: 358-369.

备注/Memo

备注/Memo:
收稿日期:2019-10-08。
基金项目:国家自然科学基金项目(61602146);浙江大学CAD&CG国家重点实验室开放课题(A1814);中央高校基本科研业务费专项(75104-036002)
作者简介:张延孔,讲师,博士研究生,主要研究方向为数据可视化、数据可解释分析;卢家品,硕士研究生,主要研究方向为数据可视化;张帅超,博士研究生,主要研究方向为交通利益预测与评估、大数据分析
通讯作者:张延孔.E-mail:zhangyankong@hfut.edu.cn
更新日期/Last Update: 2020-07-25