Short term traffic flow prediction based on multiple time series data and improved Elman neural network

2018 International Conference on Civil and Hydraulic Engineering

土木建筑工程;水利工程

Wang, Shuo^1 ; Gu, Yuanli^1 ; Rui, Xiaoping^2 ; Li, Meng^1 ; Lu, Wenqi^1

MOE Key Laboratory for Urban Transportation Complex Systems Theory and Technology, Beijing Jiaotong University, Beijing

100044, China^1

College of Resources and Environment, University of Chinese Academy of Sciences, Beijing

100049, China^2

关键词: Elman neural network;    Mind evolution algorithms;    Multiple time series;    Phase space reconstruction;    Prediction accuracy;    Short-term traffic flow;    Time-series data;    Traffic prediction;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/189/6/062033/pdf
DOI  :  10.1088/1755-1315/189/6/062033

学科分类：土木及结构工程学

来源: IOP

【 摘 要 】

To improve the short term traffic prediction precision, this paper proposes an improved Elman neural network (ELMNN) model for the prediction work. The model input includes two parts: the measured flow data and the theoretical flow data obtained by traffic occupancy and speed. Furthermore, in order to capture the inner regularity of the time series data, the theoretical flow data and the measured flow data are both reconstructed using a phase space reconstruction method. Finally, the reconstructed data are put into the improved ELMNN model, which is developed by employing the mind evolution algorithm (MEA). Compared with the original models, the results of the case study show that the proposed model can obviously improve the prediction accuracy.