Multi-level Recursive Forecasting Method for Road Accidents
-
摘要: 针对道路交通系统动态时变的特点,用多层递阶预测方法,建立了道路交通事故的多层递阶预测模型.将事故预测分解成对时变参数的预测和在此基础上对道路交通事故未来状态的预测两部分,通过对时变参数的精确预测提高事故预测精度.以1989~1999年我国某省道路交通死亡人数为原始数据建模,模拟结果显示,对2000~2001年的预测结果和实际道路交通死亡人数之间的平均误差为5.8%.Abstract: In view of the dynamic and time-varying characteristic of a traffic system,a multi-level recursive forecasting method was proposed,and a multi-level recursive forecasting model for forecasting road accidents was established.With this method,forecast of road accidents is divided into two parts: forecast of timevarying parameters and forecast of road accidents based on the former forecast.The forecasting precision is improved by precise forecasting time-varying parameters.The death toll of a province in China from 1989 to 1999 was taken as statistical data to derive the forcasting model.Simulation result shows that the average error of the forcasted death toll is 5.8% compared with the real statistical data of 2000 and 2001.
-
Key words:
- road accident /
- multi-level recursive model /
- time-varying parameter /
- forecast
-
李相勇,张南,蒋葛夫.道路交通事故灰色马尔可夫预测模型[J].公路交通科技,2003,20(4):98-104.Li X Y,Zhang N,Jiang G F.Grey-Markov model for forecasting road accidents [J].Journal of Highway and Transportation Research and Development,2003,20(4):98-104.[2] 李相勇.道路交通事故预测方法研究[D].硕士学位论文.成都:西南交通大学,2004.Li X Y.Research on forecasting method of road accidents [D].Master Degree Thesis,Chengdu:Southwest Jiaotong University,2004.[3] 李邦宪.动态系统预测的多层递阶方法[M].北京:气象出版社,1996.1-64.[4] 陈玉祥,张汉亚.预测技术与应用[M].北京:机械工业出版社,1985.31-56.[5] 韩志刚.多层递阶预报方法参数估计的初值选择[J].控制与决策,1986,1(1):27-31.
点击查看大图
计量
- 文章访问数: 1524
- HTML全文浏览量: 72
- PDF下载量: 376
- 被引次数: 0