Cover Image

Traffic speed prediction of high-frequency time series using additively decomposed components as features

Traffic speed prediction is an integral part of an Intelligent Transportation System (ITS) and the Internet of Vehicles (IoV). Advanced knowledge of average traffic speed can help take proactive preventive steps to avoid impending problems. There have been studies for traffic speed prediction in whi...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhammad Ali, Muhammad Ali, Mohamad Yusof, Kamaludin, Wilson, Benjamin, Ziegelmueller, Carina
Format: Article
Language:English
Published: John Wiley and Sons Inc 2022
Subjects:
TK Electrical engineering. Electronics Nuclear engineering
Online Access:http://eprints.utm.my/104449/1/KamaludinMohamadYusof2022_TrafficSpeedPredictionofHighFrequency.pdf
http://eprints.utm.my/104449/
http://dx.doi.org/10.1049/smc2.12027
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.104449
record_format eprints
spelling my.utm.1044492024-02-08T07:58:55Z http://eprints.utm.my/104449/ Traffic speed prediction of high-frequency time series using additively decomposed components as features Muhammad Ali, Muhammad Ali Mohamad Yusof, Kamaludin Wilson, Benjamin Ziegelmueller, Carina TK Electrical engineering. Electronics Nuclear engineering Traffic speed prediction is an integral part of an Intelligent Transportation System (ITS) and the Internet of Vehicles (IoV). Advanced knowledge of average traffic speed can help take proactive preventive steps to avoid impending problems. There have been studies for traffic speed prediction in which data has been decomposed into components using various decomposition techniques such as empirical mode decomposition, wavelets, and seasonal decomposition. As far as the authors are aware, no research has used additively decomposed components as input features. In this study, we used additive decomposition on 21,843 samples of traffic speed data. We implemented two statistical techniques designed for double seasonality (i) Double Seasonal Holt-Winter, and (ii) Trigonometric seasonality, Box-Cox transformation, autoregressive integrated moving average errors, trend, and Seasonal components (TBATS), and five machine learning (ML) techniques, (i) Multi-Layer Perceptron, (ii) Convolutional-Neural Network, (iii) Long Short-Term Memory, (iv) Gated Recurrent Unit and (v) Convolutional-Neural Network-LSTM. Machine learning techniques are used in univariate mode with raw time series as features and then with decomposed components as features in multivariate mode. This study demonstrates that using decomposed components (trend, seasonal, and residual), as features, improves prediction results for multivariate ML techniques. This becomes a significant advantage when no other features are available. John Wiley and Sons Inc 2022 Article PeerReviewed application/pdf en http://eprints.utm.my/104449/1/KamaludinMohamadYusof2022_TrafficSpeedPredictionofHighFrequency.pdf Muhammad Ali, Muhammad Ali and Mohamad Yusof, Kamaludin and Wilson, Benjamin and Ziegelmueller, Carina (2022) Traffic speed prediction of high-frequency time series using additively decomposed components as features. IET Smart Cities, 4 (2). pp. 92-109. ISSN 2631-7680 http://dx.doi.org/10.1049/smc2.12027 DOI : 10.1049/smc2.12027
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
topic TK Electrical engineering. Electronics Nuclear engineering
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Muhammad Ali, Muhammad Ali
Mohamad Yusof, Kamaludin
Wilson, Benjamin
Ziegelmueller, Carina
Traffic speed prediction of high-frequency time series using additively decomposed components as features
description Traffic speed prediction is an integral part of an Intelligent Transportation System (ITS) and the Internet of Vehicles (IoV). Advanced knowledge of average traffic speed can help take proactive preventive steps to avoid impending problems. There have been studies for traffic speed prediction in which data has been decomposed into components using various decomposition techniques such as empirical mode decomposition, wavelets, and seasonal decomposition. As far as the authors are aware, no research has used additively decomposed components as input features. In this study, we used additive decomposition on 21,843 samples of traffic speed data. We implemented two statistical techniques designed for double seasonality (i) Double Seasonal Holt-Winter, and (ii) Trigonometric seasonality, Box-Cox transformation, autoregressive integrated moving average errors, trend, and Seasonal components (TBATS), and five machine learning (ML) techniques, (i) Multi-Layer Perceptron, (ii) Convolutional-Neural Network, (iii) Long Short-Term Memory, (iv) Gated Recurrent Unit and (v) Convolutional-Neural Network-LSTM. Machine learning techniques are used in univariate mode with raw time series as features and then with decomposed components as features in multivariate mode. This study demonstrates that using decomposed components (trend, seasonal, and residual), as features, improves prediction results for multivariate ML techniques. This becomes a significant advantage when no other features are available.
format Article
author Muhammad Ali, Muhammad Ali
Mohamad Yusof, Kamaludin
Wilson, Benjamin
Ziegelmueller, Carina
author_facet Muhammad Ali, Muhammad Ali
Mohamad Yusof, Kamaludin
Wilson, Benjamin
Ziegelmueller, Carina
author_sort Muhammad Ali, Muhammad Ali
title Traffic speed prediction of high-frequency time series using additively decomposed components as features
title_short Traffic speed prediction of high-frequency time series using additively decomposed components as features
title_full Traffic speed prediction of high-frequency time series using additively decomposed components as features
title_fullStr Traffic speed prediction of high-frequency time series using additively decomposed components as features
title_full_unstemmed Traffic speed prediction of high-frequency time series using additively decomposed components as features
title_sort traffic speed prediction of high-frequency time series using additively decomposed components as features
publisher John Wiley and Sons Inc
publishDate 2022
url http://eprints.utm.my/104449/1/KamaludinMohamadYusof2022_TrafficSpeedPredictionofHighFrequency.pdf
http://eprints.utm.my/104449/
http://dx.doi.org/10.1049/smc2.12027
_version_ 1792147744452771840
score 13.211869

Similar Items