[1]于泉,刘洋,郭骁伟.基于路口相关性的交通流量修复研究[J].深圳大学学报理工版,2019,(No.3(221-346)):327-332.[doi:10.3724/SP.J.1249.2019.03229]
 YU Quan,LIU Yang,and GUO Xiaowei.Study on repair of traffic flow data based on intersections correlation[J].Journal of Shenzhen University Science and Engineering,2019,(No.3(221-346)):327-332.[doi:10.3724/SP.J.1249.2019.03229]
点击复制

基于路口相关性的交通流量修复研究()
分享到:

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
期数:
2019年No.3(221-346)
页码:
327-332
栏目:
【交通物流】
出版日期:
2019-05-20

文章信息/Info

Title:
Study on repair of traffic flow data based on intersections correlation
作者:
于泉1刘洋1郭骁伟2
1) 北京工业大学北京市交通工程重点实验室,北京 100124;2) 中国公路工程咨询集团有限公司,北京 100124
Author(s):
YU Quan1 LIU Yang1 and GUO Xiaowei2
1) Beijing Key Laboratory of Traffic Engineering, Beijing University of Technology, Beijing 100124, P.R.China2) China Highway Engineering Consulting Corporation, Beijing 100124, P.R.China
关键词:
绿波协调路口相关性主成分分析RBF神经网络交通流量修复
Keywords:
green wave coordinate intersections correlation principal component analysis (PCA) radical basis function (RBF) neural network traffic flow reparation
分类号:
U 491;TP 308
DOI:
10.3724/SP.J.1249.2019.03229
文献标志码:
A
摘要:
为实现对交通流异常数据的有效修复,根据流量—占有率函数模型,利用主成分分析法对绿波协调控制交叉口群中各路口的占有率参数进行相关性分析,间接得到各路口流量相关性的大小,构建相关路口集;根据相关路口集的历史数据,分别利用流量—占有率模型、径向基函数神经网络模型以及基于两种方法的组合模型对目标路口的缺失交通流数据进行修复;最后在实例分析的基础上,对模型性能进行验证.结果表明:组合模型与其他两种方法相比,可更精确地进行交通数据修复,在实际数据验证中表现出更好的适应性.
Abstract:
In order to effectively repair the fault data of traffic flow, according to the function model of flow-occupancy, we use the PCA (principal component analysis) method to analyze the correlation coefficient of occupancy of each intersection in signalized intersections under green wave coordinated control, and indirectly obtain the correlation of traffic flow data at each intersection. Finally, we construct the relevant intersection set. According to the historical data of the relevant intersection set, we repair the missing traffic flow data of the target intersection by the traffic-occupancy model, the radical basis function (RBF) neural network model, and the model combined by the two models, respectively. The three models’ performances are verified on the basis of the example analysis. The results show that the combined model can be used to repair traffic data more accurately than the other two models and may have better adaptability in actual data validation.
更新日期/Last Update: 2019-04-22