JZUS - Journal of Zhejiang University SCIENCE

Frontiers of Information Technology & Electronic Engineering

Accepted manuscript available online (unedited version)

Online transfer learning with an MLP-assisted graph convolutional network for traffic flow forecasting: a solution for edge intelligent devices

Author(s): Jingru SUN¹, Chendingying LU¹, Yichuang SUN², Hongbo JIANG¹, Zhu XIAO¹
Affiliation(s): ¹College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China; more
Corresponding email(s): jt_sunjr@hnu.edu.cn
Key Words: Online transfer learning; Traffic forecasting; Intelligent edge devices

Share this article to： More <<< Previous Paper \|Next Paper >>>

Jingru SUN¹, Chendingying LU¹, Yichuang SUN², Hongbo JIANG¹, Zhu XIAO¹. Online transfer learning with an MLP-assisted graph convolutional network for traffic flow forecasting: a solution for edge intelligent devices[J]. Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/FITEE.2401059

@article{title="Online transfer learning with an MLP-assisted graph convolutional network for traffic flow forecasting: a solution for edge intelligent devices",
author="Jingru SUN¹, Chendingying LU¹, Yichuang SUN², Hongbo JIANG¹, Zhu XIAO¹",
journal="Frontiers of Information Technology & Electronic Engineering",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/FITEE.2401059"
}

%0 Journal Article
%T Online transfer learning with an MLP-assisted graph convolutional network for traffic flow forecasting: a solution for edge intelligent devices
%A Jingru SUN¹
%A Chendingying LU¹
%A Yichuang SUN²
%A Hongbo JIANG¹
%A Zhu XIAO¹
%J Frontiers of Information Technology & Electronic Engineering
%P
%@ 2095-9184
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/FITEE.2401059"

TY - JOUR
T1 - Online transfer learning with an MLP-assisted graph convolutional network for traffic flow forecasting: a solution for edge intelligent devices
A1 - Jingru SUN¹
A1 - Chendingying LU¹
A1 - Yichuang SUN²
A1 - Hongbo JIANG¹
A1 - Zhu XIAO¹
J0 - Frontiers of Information Technology & Electronic Engineering
SP -
EP -
%@ 2095-9184
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/FITEE.2401059"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: Traffic flow prediction is crucial for intelligent transportation and aids in route planning and navigation.However, existing studies often focus on prediction accuracy improvement, while neglecting external influences and practical issues like resource constraints and data sparsity on edge devices. We propose an online transfer learning (OTL) with multi-layer perceptron (MLP)-assisted graph convolutional network (GCN) framework (OTL-GM),consisting of two parts: transferring source domain features to edge devices and using online learning to bridge domain gaps. Experiments on four datasets demonstrate OTL’s effectiveness, and in a comparison with a model without OTL, convergence time of the OTL-model increased from 24.77% to 95.32%.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference