基于GBRT模型的交通事故预测

杨文忠; 张志豪; 柴亚闯; 温杰彬; 杨蒙蒙; 富雅玲

doi:10.13568/j.cnki.651094.651316.2019.11.19.0001

您当前的位置：

首页 >

文章列表页 >

基于GBRT模型的交通事故预测

信息科学与技术 | 更新时间：2026-01-19

- 基于GBRT模型的交通事故预测
- 基于GBRT模型的交通事故预测
- 新疆大学学报（自然科学版中英文） 2020年37卷第1期页码：36-43
- 作者机构：
  
  新疆大学信息科学与工程学院
- 作者简介：
- 基金信息：
  
  新疆维吾尔自治区自然科学基金项目“高速公路VANET预警信息广播传输机制研究”(2017D01C042)
- DOI：10.13568/j.cnki.651094.651316.2019.11.19.0001
  中图分类号： U491.31
- 纸质出版：2020
- 稿件说明：
移动端阅览
[1]杨文忠,张志豪,柴亚闯,等.基于GBRT模型的交通事故预测[J].新疆大学学报(自然科学版)(中英文),2020,37(01):36-43.
[1]杨文忠,张志豪,柴亚闯,等.基于GBRT模型的交通事故预测[J].新疆大学学报(自然科学版)(中英文),2020,37(01):36-43. DOI： 10.13568/j.cnki.651094.651316.2019.11.19.0001.

DOI：10.13568/j.cnki.651094.651316.2019.11.19.0001.

摘要

道路交通安全水平的重要标志就是道路交通事故发生量.为解决当前交通事故量预测精度不高、时间拐点数据预测效果差的问题

以及在交通管理系统中提供更加准确的预测数据帮助交通管理部门做出科学的决策

本文针对我国年周期交通事故建立了基于GBRT(Gradient Boosted Regression Tree)的交通事故模型.通过训练交通事故相关数据对未来交通事故死亡人数进行预测

并与多种回归模型、神经网络模型进行对比实验

结果显示GBRT模型具有拟合效果佳、训练时间短、高鲁棒性的优势

能够更准确、高效的对交通事故安全水平进行预测.

Abstract

The important manifestation of road traffic safety level is the amount of road traffic accidents. In view of the problem that the current traffic accident volume prediction accuracy is not high

the time in?ection point data prediction effect is poor

and provide more accurate prediction data to the traffic management department

help make scienti?c decisions in the traffic management system

this paper established a traffic accident model based on GBRT(Gradient Boosted Regression Tree) for China's annual traffic accidents

and predicts the number of traffic accident deaths in China by training traffic accident related data.Compared with various regression models and neural network models

the results show that the GBRT model has the advantages of best ?tting effect

short training time and high robustness

which can predict traffic accident safety level more accurately and efficiently.

关键词

Keywords

references

BURNETT R A, DONG S. Prediction of Injuries and Fatalities in Aviation Accidents through Machine Learning[C]//The International Conference, ACM, 2017:60-68.

DENG J L. Introduction to Grey system theory[J]. Journal of Grey System, 1989(1):1-24.

CHUKWUTOO C Ihueze, UCHENDU O Onwurah. Road traffic accidents prediction modelling:An analysis of Anambra State,Nigeria[J]. Accident Analysis&Prevention, 2018, 112:21-29.

杨鑫刚,李德生,任国友.基于残差修正灰色预测模型的北京市道路交通事故预测分析[J].数学的实践与认识, 2018, 48(3):159-166.YANG X G, LI D S, REN G Y. Prediction and Analysis of Beijing Road Traffic Accidents Based on Residual Correction Grey Prediction Model[J]. Mathematics in Practice and Theory, 2018, 48(3):159-166.(in Chinese)

DAI L L, GU J G, YU C J. Improvement and application of grey prediction model for road traffic accident[C]//Eighth International Conference on Fuzzy Systems and Knowledge Discovery. IEEE, 2011:2040-2043.

李梦婉,沙秀艳.基于GM(1,1)灰色预测模型的改进与应用[J].计算机工程与应用, 2016, 52(4):24-30.LI M W, SHA X Y. Application of improved GM(1,1)grey prediction model[J]. Computer Engineering andApplications, 2016,52(4):24-30.(in Chinese)

王福建,李铁强,俞传正.道路交通事故灰色Verhulst预测模型[J].交通运输工程学报, 2006, 6(1):122-126.WANG F J, LI T Q, YU C Z. Grey Verhulst Predictive Model of Road Traffic Accidents[J]. Journal of Traffic and Transportation Engineering, 2006, 6(1):122-126.(in Chinese)

赵玲,许宏科,程鸿亮.基于最优加权组合模型的道路交通事故预测[J].计算机工程与应用, 2013, 49(24):11-15.ZHAO L, XU H K, CHENG H L. Road traffic accidents prediction based on optimal weighted combined model[J]. Computer Engineering and Applications, 2013, 49(24):11-15.(in Chinese)

安杰,董龙洋.基于BP神经网络的道路交通安全预测模型研究[J].公路与汽运, 2014(3):63-67.AN J, DONG L Y. Research on Road Traffic Safety Prediction Model Based on BP Neural Network[J]. Highways&Automotive Applications, 2014(3):63-67.(in Chinese)

胡立伟,张婷,郭凤香,等.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+397.HU L W, ZHANG T, GUO F X, et al. 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), 2018,42(3):388-392+397.(in Chinese)

赵玲,许宏科.基于新维无偏灰色马尔可夫的交通事故预测[J].计算机工程与应用, 2013, 49(7):35-38+59.ZHAO L, XU H K. Traffic Accident Prediction Based on New Dimension Unbiased Grey Markov[J]. Computer Engineering and Applications, 2013, 49(7):35-38+59.(in Chinese)

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+259.ZHANG Z H, YANG W Z, YUAN T T, et al.Traffic accident prediction based on LSTM neural network model[J]. Computer Engineering and Applications, 2019, 55(14):249-253+259.(in Chinese)

HOCHREITER S, SCHMIDHUBER J. Long short-term memory[M]. Supervised Sequence Labelling with Recurrent Neural Networks. Springer Berlin Heidelberg, 1997:1735-1780.

JEROME HFriedman. Greedy function approximation:a gradient boosting machine[J]. The Annals of Statistics, 2001, 29(5):1189-1232.

李航.统计学习方法[M].北京:清华大学出版社, 2012.Li Hang. Statistical learning method[M]. Beijing:Tsinghua University Press, 2012.(in Chinese)

裴玉龙,蒋贤才,程国柱,等.道路交通事故分析与再现技术[M].北京:人民交通出版社, 2013.PEI Y L, JIANG X C, CHENG G Z. Road traffic accident analysis and reproduction technology[M]. Beijing:China Communications Press, 2013.(in Chinese)

WANG H, PARRISH A, SMITH R K, et al. Variable selection and ranking for analyzing automobile traffic accident data[C]//ACM Symposium on Applied Computing. ACM, 2005:32-37.

浏览量

557

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

应用线性回归方法对无形资产进行收益预测

基于改进蛙跳算法优化的支持向量回归机ORP预测