|本期目录/Table of Contents|

[1]金杰灵,史晨军,邓院昌.基于Hankel-DMD的城市交通事故风险时空预测*[J].中国安全生产科学技术,2022,18(8):18-23.[doi:10.11731/j.issn.1673-193x.2022.08.003]
 JIN Jieling,SHI Chenjun,DENG Yuanchang.Spatio-temporal prediction of urban traffic accident risk based on Hankel-DMD[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(8):18-23.[doi:10.11731/j.issn.1673-193x.2022.08.003]
点击复制

基于Hankel-DMD的城市交通事故风险时空预测*
分享到:

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
18
期数:
2022年8期
页码:
18-23
栏目:
学术论著
出版日期:
2022-08-31

文章信息/Info

Title:
Spatio-temporal prediction of urban traffic accident risk based on Hankel-DMD
文章编号:
1673-193X(2022)-08-0018-06
作者:
金杰灵史晨军邓院昌
(1.中南大学 交通运输工程学院,湖南 长沙 410075;
2.肇庆市交通运输局,广东 肇庆 526060;
3.中山大学 智能工程学院,广东 广州 510006)
Author(s):
JIN Jieling SHI Chenjun DENG Yuanchang
(1.School of Traffic and Transportation Engineering,Central South University,Changsha Hunan 410075,China;
2.Zhaoqing Transportation Bureau,Zhaoqing Guangdong 526060,China;
3.School of Intelligent Engineering,Sun Yet-sen University,Guangzhou Guangdong 510006,China)
关键词:
交通事故风险时空预测动态模态分解总最小二乘法Hankel矩阵
Keywords:
traffic accident risk spatio-temporal prediction dynamic mode decomposition total least squares Hankel matrix
分类号:
X951
DOI:
10.11731/j.issn.1673-193x.2022.08.003
文献标志码:
A
摘要:
为解决城市交通事故风险时空分布预测任务中时空关联性捕捉困难的问题,提出基于动态模态分解(DMD)的城市交通事故分析时空预测模型,模型利用总最小二乘法去除交通事故数据中的噪声,应用结合Hankel矩阵的动态模态分解模型(Hankel-DMD)捕捉交通事故风险的时空关联性,对交通事故风险的时空分布进行预测。研究结果表明:DMD框架能够为高维预测任务提供低秩解决方案,从高维数据中捕捉时空关联性;Hankel-DMD模型在预测评价指标平均绝对误差和均方根误差方面的表现明显优于统计学及机器学习等方法;Hankel-DMD模型产生的动态模态和特征值,对事故风险系统的时空动态特征具有一定的可解释性,同时验证Hankel-DMD模型的适用性。
Abstract:
To solve the difficulty of capturing spatio-temporal correlation in the task of predicting the spatio-temporal distribution of urban traffic accident risk,a spatio-temporal prediction model of urban traffic accident analysis based on the dynamic mode decomposition (DMD) was proposed.In this model,the noise in the traffic accident data was removed by the total least squares method,and the spatio-temporal correlation of traffic accident risk was captured by the dynamic mode decomposition model with Hankel matrix (Hankel-DMD),thereby the spatio-temporal distribution of traffic accident risk was predicted.The results showed that the DMD framework could not only provide a general low-rank solution for high-dimensional prediction tasks,but also capture the spatio-temporal correlation from high-dimensional data.The Hankel-DMD model performed significantly better than the common methods such as statistics,machine learning and deep learning in terms of the mean absolute error and root mean square error of the prediction evaluation indexes.Moreover,the dynamic modes and eigenvalues generated by the Hankel-DMD model had some interpretability for the spatio-temporal dynamic characteristics of the accident risk system,which demonstrated the applicability of the Hankel-DMD model for the spatio-temporal prediction tasks of urban traffic accident risk.

参考文献/References:

[1]World Health Organization.Road traffic injries[EB/OL].(2021-06-21)[2021-06-21].https://www.who.int/news-room/fact-sheets/detail/road-traffic-injuries.
[2]REN H,SONG Y,WANG J,et al.A deep learning approach to the citywide traffic accident risk prediction[J].2017,11(21)110-130.
[3]YU L,DU B,HU X,et al.Deep spatio-temporal graph convolutional network for traffic accident prediction[J].Neurocomputing,2021,423:135-147.
[4]YUAN Z,ZHOU X,YANG T.Hetero-ConvLSTM:a deep learning approach to traffic accident prediction on heterogeneous spatio-temporal data[C]//The 24th ACM SIGKDD International Conference,ACM,2018.
[5]RABBANI M B A,MUSARAT M A,ALALOUL W S,et al.A comparison between Seasonal Autoregressive Integrated Moving Average (SARIMA) and Exponential Smoothing (ES) based on time series model for forecasting road accidents[J].Arabian Journal for Science and Engineering,2021,46(11):11113-11138.
[6]MICHALAKI P,QUDDUS M,PITFIELD D,et al.A time-series analysis of motorway collisions in England considering road infrastructure,socio-demographics,traffic and weather characteristics[J].Journal of Transport & Health,2016,3(1):9-20.
[7]DONG N,HUANG H,ZHENG L.Support vector machine in crash prediction at the level of traffic analysis zones:assessing the spatial proximity effects[J].Accident Analysis & Prevention,2015,82:192-198.
[8]SHAO X,BOEY L L,LUO Y.Traffic accident time series prediction model based on combination of ARIMA and BP and SVM[J].Journal of Traffic and Logistics Engineering,2019,7(2):622-630.
[9]YU B,WANG Y T,YAO J B,et al.A comparison of the performance of ANN and SVM for the prediction of traffic accident duration[J].Neural Network World,2016,26(3):271-279.
[10]SCHMID P J.Dynamic mode decomposition of numerical and experimental data[J].Journal of Fluid Mechanics,2010,656:5-28.
[11]PROCTOR J L,ECKHOFF P A.Discovering dynamic patterns from infectious disease data using dynamic mode decomposition[J].International Health,2015,7(2):139-145.
[12]HUA J C,ROY S,MCCAULEY J L,et al.Using dynamic mode decomposition to extract cyclic behavior in the stock market[J].Physic A:Statistical Mechanics and Its Applications,2016,448:172-180.
[13]KUTZ J N,BRUNTON S L,BRUNTON B W,et al.Dynamic mode decomposition:data-driven modeling of complex systems[M].Society for Industrial and Applied Mathematics,2016.
[14]VASCONCELOS F E,DOS S P L.A dynamic mode decomposition approach with hankel blocks to forecast multi-channel temporal series[J].IEEE,Control Systems Letters,2019,3(3):739-744.
[15]FIERRO R D,GOLUB G H,HANSEN P C,et al.Regularization by truncated total least squares[J].SIAM Journal on Scientific Computing,1997,18(4):1223-1241.
[16]WILLMOTT C J,MATSUURA K.Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance[J].Climate Research,2005,30(1):79-82.
[17]KUTZ J N.Data-driven modeling & scientific computation:methods for complex systems & big data[M].Oxford University Press,2013.
[18]TU J H.Dynamic mode decomposition:theory and applications[D].Princeton:Princeton University,2013.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期: 2022-03-23
* 基金项目: 国家自然科学基金项目(U1611461)
作者简介: 金杰灵,博士研究生,主要研究方向为交通安全。
通信作者: 史晨军,硕士,助理工程师,主要研究方向为交通安全,交通心理学。
更新日期/Last Update: 2022-09-19