正在加载图片...
第15卷第4期 智能系统学报 Vol.15 No.4 2020年7月 CAAI Transactions on Intelligent Systems Jul.2020 D0L:10.11992tis.201910002 基于路网结构的城市交通事故短期风险预测方法 张延孔,卢家品',张帅超2,姬晓鹏2,罗月童',陈为 (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) 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 predic- tion 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,诚少交通事故的发生。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。 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 中图分类号:TP18文献标志码:A文章编号:1673-4785(2020)04-0663-09 中文引用格式: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. 英文引用格式:ZHANG Yankong,LUJiapin,ZHANG Shuaichao,.etal.A short--term risk prediction method for urban traffic acci- dents based on road network[Jl.CAAI transactions on intelligent systems,2020,15(4):663-671. A short-term risk prediction method for urban traffic accidents based on road network ZHANG Yankong',LU Jiapin',ZHANG Shuaichao,JI Xiaopeng',LUO Yuetong',CHEN Wei? (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) Abstract:Urban traffic accidents usually occur on public roads.However,the existing traffic accident risk prediction al- gorithms 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 ac- cident 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 exist- ing ones in accuracy,precision and false negative rate (FNR). Keywords:GCNN;traffic accident;accident mode;multi-source data;risk forecasting;road network structure;LSTM; smart city 世界卫生组织在2015年发表的《全球道路 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 安全状况报告》四中指出每年约有125万人死于 CAD&CG国家重点实验室开放课题(A1814):中央 交通事故。通过交通大数据,识别交通事故中的 高校基本科研业务费专项(75104-036002). 通信作者:张延孔.E-mail:zhangyankong@hfut.edu.cm. 规律并加以治理和预防已成为交通领域重要的研DOI: 10.11992/tis.201910002 基于路网结构的城市交通事故短期风险预测方法 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) 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 predic￾tion 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。 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 中图分类号:TP18 文献标志码:A 文章编号:1673−4785(2020)04−0663−09 中文引用格式: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. 英文引用格式:ZHANG Yankong, LU Jiapin, ZHANG Shuaichao, et al. A short-term risk prediction method for urban traffic acci￾dents based on road network[J]. CAAI transactions on intelligent systems, 2020, 15(4): 663–671. A short-term risk prediction method for urban traffic accidents based on road network 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) Abstract: Urban traffic accidents usually occur on public roads. However, the existing traffic accident risk prediction al￾gorithms 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 ac￾cident 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 exist￾ing ones in accuracy, precision and false negative rate (FNR). Keywords: GCNN; traffic accident; accident mode; multi-source data; risk forecasting; road network structure; LSTM; smart city 世界卫生组织在 2015 年发表的《全球道路 安全状况报告》[1] 中指出每年约有 125 万人死于 交通事故。通过交通大数据,识别交通事故中的 规律并加以治理和预防已成为交通领域重要的研 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). 通信作者:张延孔. E-mail:zhangyankong@hfut.edu.cn. 第 15 卷第 4 期 智 能 系 统 学 报 Vol.15 No.4 2020 年 7 月 CAAI Transactions on Intelligent Systems Jul. 2020
向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有