Multivariable traffic flow prediction model based on convolutional neural network and gate recurrent unit

doi:10.11835/j.issn.1000-582X.08.013

Home > Archive>Volume 46, Issue 8, 2023 >132-140. DOI:10.11835/j.issn.1000-582X.08.013

Multivariable traffic flow prediction model based on convolutional neural network and gate recurrent unit
DOI:
                        10.11835/j.issn.1000-582X.08.013
                    
CSTR:
                        [cstr]
                    
Author:
                        WANG Bowen1WANG Bowen
a. School of Traffic Management; 1b. School of Information Network Security, People’s Public Security University of China, Beijing 100038, P. R. China; 2. Department of Electrical Information, Shandong University of Science and Technology, Jinan 250000, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
WANG Jingsheng1WANG Jingsheng
a. School of Traffic Management; 1b. School of Information Network Security, People’s Public Security University of China, Beijing 100038, P. R. China; 2. Department of Electrical Information, Shandong University of Science and Technology, Jinan 250000, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
WANG Tongyi3WANG Tongyi

Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
XIA Tianyu2XIA Tianyu

Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
ZHao Danting1ZHao Danting
a. School of Traffic Management; 1b. School of Information Network Security, People’s Public Security University of China, Beijing 100038, P. R. China; 2. Department of Electrical Information, Shandong University of Science and Technology, Jinan 250000, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site

                    
Affiliation:1.a. School of Traffic Management; 1b. School of Information Network Security, People’s Public Security University of China, Beijing 100038, P. R. China; 2. Department of Electrical Information, Shandong University of Science and Technology, Jinan 250000, P. R. China
Clc Number:TP183;U491.14
Fund Project:Supported by Public Security Theory and Soft Science Research Project of Ministry of Public Security(2020LLYJGADX020), and Project of Basic Theory System of Basic Scientific Research Discipline of People’s Public Security University of China (2022JKF02013).

Article

Figures

Metrics

Reference

Cited by

Materials

Comments

Abstract:

For multi-step forecasting of traffic flow, a convolutional neural networks (CNN)-gate recurrent unit (GRU) model based on encoder-decoder (ED) framework was proposed, referred to as the ED CNN-GRU model. In this model, CNN serves as the encoder, capturing information from the traffic flow sequence, which is then interpreted and outputted by the GRU decoder. Experimental results show that compared with CNN and GRU models, ED framework effectively solves the problem of rapid error accumulation. Compared with other benchmark models, CNN and GRU models are superior in feature extraction and interpretation of traffic flow series. In terms of the traffic flow prediction task of 12 steps in the future, compared with other benchmark models, the root mean square error of the univariate input ED CNN-GRU model is reduced by about 0.344 to 6.464, and the mean absolute error is reduced by about 0.192 to 0.425. Additionally, compared with univariate input, the ED CNN-GRU model with multivariate input exhibits a better fitting performance. These findings confirm that ED CNN-GRU model possesses strong forecasting capabilities for multi-step traffic flow forecasting tasks with varying input dimensions, and provides a multi-step traffic flow forecasting model that supports both univariate and multivariate input for cities with diverse data acquisition conditions.

Key words:traffic flow prediction;CNN;GRU;encoder-decoder;multi-step prediction

Get Citation

王博文,王景升,王统一,夏天雨,赵丹婷.基于卷积神经网络与门控循环单元的交通流预测模型[J].重庆大学学报,2023,46(8):132~140

Copy

Article Metrics

Abstract:
PDF:
HTML:
Cited by:

History

Received:July 28,2021
Revised:
Adopted:
Online: August 25,2023
Published:

Home

Get Citation

Share

Article Metrics

History

Article QR Code