Multi-component Spatial-temporal Graph Convolution Networks for Traffic Flow Forecasting

doi:10.13328/j.cnki.jos.005697

微信服务号

微信订阅号

2025-4-21- 15

Home > Archive>Volume 30, Issue 3, 2019 >759-769. DOI:10.13328/j.cnki.jos.005697

PDF HTML XML Export Cite reminder

Multi-component Spatial-temporal Graph Convolution Networks for Traffic Flow Forecasting
DOI:
                        10.13328/j.cnki.jos.005697
                    
Author:
                        FENG NingFENG Ning
School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China;Beijing Key Laboratory of Traffic Data Analysis and Mining(Beijing Jiaotong University), Beijing 100044, China
Find this author on CNKI
Find this author on BaiDu
Search for this author on this site
GUO Sheng-NanGUO Sheng-Nan
School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China;Beijing Key Laboratory of Traffic Data Analysis and Mining(Beijing Jiaotong University), Beijing 100044, China
Find this author on CNKI
Find this author on BaiDu
Search for this author on this site
SONG ChaoSONG Chao
School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China;Beijing Key Laboratory of Traffic Data Analysis and Mining(Beijing Jiaotong University), Beijing 100044, China
Find this author on CNKI
Find this author on BaiDu
Search for this author on this site
ZHU Qi-ChaoZHU Qi-Chao
School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China;Beijing Key Laboratory of Traffic Data Analysis and Mining(Beijing Jiaotong University), Beijing 100044, China
Find this author on CNKI
Find this author on BaiDu
Search for this author on this site
WAN Huai-YuWAN Huai-Yu
School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China;Beijing Key Laboratory of Traffic Data Analysis and Mining(Beijing Jiaotong University), Beijing 100044, China
Find this author on CNKI
Find this author on BaiDu
Search for this author on this site

                    
Affiliation:
Clc Number:
Fund Project:National Natural Science Foundation of China (61603028)

Article

Figures

Metrics

Reference

Cited by

Materials

Comments

Abstract:

Forecasting the traffic flows is a hot issue for researchers and practitioners in the transportation field. It is very challenging to forecast the traffic flows due to the high nonlinearity and complexity of the data, and most of the existing methods cannot effectively capture the spatial-temporal correlations of traffic flow data. In this paper, we propose a novel deep learning based model, multi-component spatial-temporal graph convolution networks (MCSTGCN), to solve the problem of traffic flow forecasting. MCSTGCN employs three components to respectively model the recent, daily and weekly characteristics of traffic flow data. Each component uses graph convolutions in the spatial dimension and convolutions in the temporal dimension to effectively capture the spatial-temporal correlations of traffic data. Experiments on a public California freeway dataset show that the prediction performance of the MCSTGCN model is better than other existing prevalent methods.

Key words:traffic flow forecasting;spatial-temporal correlation;graph convolutional network;multi-component fusion

Get Citation

冯宁,郭晟楠,宋超,朱琪超,万怀宇.面向交通流量预测的多组件时空图卷积网络.软件学报,2019,30(3):759-769

Copy

Article Metrics

Abstract:
PDF:
HTML:
Cited by:

History

Received:July 20,2018
Revised:September 20,2018
Adopted:
Online: March 06,2019
Published:

You are the firstVisitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address：4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code：100190
Phone：010-62562563 Fax：010-62562533 Email：jos@iscas.ac.cn
Technical Support：Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063

微信服务号

微信订阅号

Get Citation

Share

微信扫一扫：分享

Article Metrics

History