Robust temporal low‐rank representation for traffic data recovery via fused lasso
Abstract Achieving complete and accurate traffic data as input is crucial for most intelligent transportation systems. However, due to hardware or software malfunction, traffic data is inevitably faced with missing and noise problems. Most of the existing representation‐based traffic data recovery m...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-02-01
|
Series: | IET Intelligent Transport Systems |
Online Access: | https://doi.org/10.1049/itr2.12010 |
id |
doaj-9fcd792853184b6e881c0ad07267104a |
---|---|
record_format |
Article |
spelling |
doaj-9fcd792853184b6e881c0ad07267104a2021-07-14T13:25:46ZengWileyIET Intelligent Transport Systems1751-956X1751-95782021-02-0115217518610.1049/itr2.12010Robust temporal low‐rank representation for traffic data recovery via fused lassoRuyong Mao0Zhengyu Chen1Guobing Hu2College of Electronic and Optical Engineering Nanjing University of Posts and Telecommunications Nanjing ChinaSchool of Electronic and Information Engineering Jinling Institute of Technology Nanjing ChinaSchool of Electronic and Information Engineering Jinling Institute of Technology Nanjing ChinaAbstract Achieving complete and accurate traffic data as input is crucial for most intelligent transportation systems. However, due to hardware or software malfunction, traffic data is inevitably faced with missing and noise problems. Most of the existing representation‐based traffic data recovery methods adopt sparse representation theory, which well models the local association properties of traffic data, but ignores their global correlation. To overcome this shortcoming, a robust low‐rank representation method that incorporates temporal prior information to impute the missing traffic data is proposed. Specifically, the low‐rank representation theory is first employed to model the global spatial correlation of traffic data, and then the fused lasso regularisation is utilized to fit the temporal correlation of traffic data. In addition, to make the proposed model more robust, F‐norm regularisation is used to smooth the Gaussian noise of traffic data. Furthermore, an efficient optimisation algorithm based on ADMM is developed to solve the proposed model. Finally, the extensive experiments performed on real dataset validate the effectiveness of the proposed method.https://doi.org/10.1049/itr2.12010 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ruyong Mao Zhengyu Chen Guobing Hu |
spellingShingle |
Ruyong Mao Zhengyu Chen Guobing Hu Robust temporal low‐rank representation for traffic data recovery via fused lasso IET Intelligent Transport Systems |
author_facet |
Ruyong Mao Zhengyu Chen Guobing Hu |
author_sort |
Ruyong Mao |
title |
Robust temporal low‐rank representation for traffic data recovery via fused lasso |
title_short |
Robust temporal low‐rank representation for traffic data recovery via fused lasso |
title_full |
Robust temporal low‐rank representation for traffic data recovery via fused lasso |
title_fullStr |
Robust temporal low‐rank representation for traffic data recovery via fused lasso |
title_full_unstemmed |
Robust temporal low‐rank representation for traffic data recovery via fused lasso |
title_sort |
robust temporal low‐rank representation for traffic data recovery via fused lasso |
publisher |
Wiley |
series |
IET Intelligent Transport Systems |
issn |
1751-956X 1751-9578 |
publishDate |
2021-02-01 |
description |
Abstract Achieving complete and accurate traffic data as input is crucial for most intelligent transportation systems. However, due to hardware or software malfunction, traffic data is inevitably faced with missing and noise problems. Most of the existing representation‐based traffic data recovery methods adopt sparse representation theory, which well models the local association properties of traffic data, but ignores their global correlation. To overcome this shortcoming, a robust low‐rank representation method that incorporates temporal prior information to impute the missing traffic data is proposed. Specifically, the low‐rank representation theory is first employed to model the global spatial correlation of traffic data, and then the fused lasso regularisation is utilized to fit the temporal correlation of traffic data. In addition, to make the proposed model more robust, F‐norm regularisation is used to smooth the Gaussian noise of traffic data. Furthermore, an efficient optimisation algorithm based on ADMM is developed to solve the proposed model. Finally, the extensive experiments performed on real dataset validate the effectiveness of the proposed method. |
url |
https://doi.org/10.1049/itr2.12010 |
work_keys_str_mv |
AT ruyongmao robusttemporallowrankrepresentationfortrafficdatarecoveryviafusedlasso AT zhengyuchen robusttemporallowrankrepresentationfortrafficdatarecoveryviafusedlasso AT guobinghu robusttemporallowrankrepresentationfortrafficdatarecoveryviafusedlasso |
_version_ |
1721302726362529792 |