[1]杨高飞,徐睿,秦鸣,等.基于ARMA和卡尔曼滤波的短时交通预测[J].郑州大学学报(工学版),2017,38(02):36.[doi:10.13705/j.issn.1671-6833.2017.02.009]
 Yang Gaofei,Xu Rui,Qin Ming,et al.Short-term Traffic Volume Forecasting Based on ARMA and Kalman Filter[J].Journal of Zhengzhou University (Engineering Science),2017,38(02):36.[doi:10.13705/j.issn.1671-6833.2017.02.009]
点击复制

基于ARMA和卡尔曼滤波的短时交通预测()
分享到:

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
38卷
期数:
2017年02期
页码:
36
栏目:
出版日期:
2017-04-28

文章信息/Info

Title:
Short-term Traffic Volume Forecasting Based on ARMA and Kalman Filter
作者:
杨高飞徐睿秦鸣郑凯俐张兵
1.华东交通大学土木建筑学院,江西南昌,330013,2.重庆交通大学交通运输学院,重庆,400074
Author(s):
Yang Gaofei1Xu Rui1Qin Ming1Zheng Kaili2Zhang Bing1
1. School of Civil Engineering, East China Jiaotong University, Nanchang, Jiangxi, 330013; 2. School of Transportation, Chongqing Jiaotong University, Chongqing, 400074
关键词:
智能交通短时交通预测ARMA卡尔曼滤波预测误差
Keywords:
DOI:
10.13705/j.issn.1671-6833.2017.02.009
文献标志码:
A
摘要:
交通预测是智能交通运输系统研究中的一个重要组成部分.为了有效地获取短时交通流量预测数据,保障交叉口畅通,依据道路情况的不确定性以及交通流的非线性变化,应用ARMA模型及卡尔曼滤波模型通过预测结果误差大小来组合预测路段短时交通流量.实例表明,组合模型预测结果达到较高的预测精度,预测误差降低到了5.79%,并且比单一模型预测精度要高.通过该组合模型可以更准确地预测短时交通流量,同时也可以为交叉口信号配时提供必要的理论依据和技术指导,对减小交通延误,提高道路服务水平有一定的应用价值.
Abstract:
The traffic prediction was an important component in the intelligent transportation system.The effective short-term traffic flow prediction was conducive to ensure the intersection unimpeded and reduce the traffic delay.According to the uncertainty of road conditions and the nonlinear change of traffic flow,the ARMA model and kalman filter mode was combined through the error magnitude of predicting results to predict the short-term traffic flow in the road.The example indicated that the combined model could achieve the higher prediction precision and made the prediction accuracy up to 5.79 percent.Besides,the combined model had an advantage over the single model in the forecasting accuracy.The combined model can not only predict the short-term traffic flow more accurately,but provided the necessary theoretical basis and technical guidance for the intersection signal timing.Besides,it had definitely application value in reducing the traffic delay and improving the road service level.

相似文献/References:

[1]曾庆山,全书鹏,靳志强..融合BP神经网络与ARIMA的短时交通流预测[J].郑州大学学报(工学版),2011,32(04):60.[doi:10.3969/j.issn.1671-6833.2011.04.015]

更新日期/Last Update: