Traffic speed prediction using GARCH‐GRU hybrid model
Abstract Traffic speed prediction is an integral part of an intelligent transportation system (ITS) because an advanced knowledge of traffic speed can help taking proactive preventive steps to avoid impending problems and it can also help in trip planning. Traffic speed data comprises a time series...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2023-11-01
|
Series: | IET Intelligent Transport Systems |
Subjects: | |
Online Access: | https://doi.org/10.1049/itr2.12411 |
_version_ | 1797615873810235392 |
---|---|
author | Muhammad Ali Kamaludin Mohamad Yusof Benjamin Wilson Carina Ziegelmueller |
author_facet | Muhammad Ali Kamaludin Mohamad Yusof Benjamin Wilson Carina Ziegelmueller |
author_sort | Muhammad Ali |
collection | DOAJ |
description | Abstract Traffic speed prediction is an integral part of an intelligent transportation system (ITS) because an advanced knowledge of traffic speed can help taking proactive preventive steps to avoid impending problems and it can also help in trip planning. Traffic speed data comprises a time series that may be modelled using any statistical or machine learning technique. In most of the cases, however, the performance of such models is bottlenecked due to heteroskedasticity usually present in such datasets. ARCH/GARCH family of models are generally used to model variance in such data. This paper presents a novel technique, termed as GARCH‐GRU, based on additive decomposition that splits data into random (residual) and deterministic parts. Random part is normalized using rolling standard deviation. GARCH (1, 1) is used to predict conditional variance of the residual and the predicted variance is then used in the basic model equation along with normalized residual that mimic white noise as required by the model. The data other than residual is modelled using a GRU model. The approach is applied to two datasets corresponding to a downtown road and a motorway. For comparison, the same datasets are exposed to three classical techniques; seasonal ARIMA, CNN and GRU techniques. The results demonstrate that the GARCH‐GRU technique outperforms others for random data of downtown road but fails to handle dynamic variations present in the motorway data. |
first_indexed | 2024-03-11T07:33:10Z |
format | Article |
id | doaj.art-a5e154f8b9734a2e9c73d76eab2c8908 |
institution | Directory Open Access Journal |
issn | 1751-956X 1751-9578 |
language | English |
last_indexed | 2024-03-11T07:33:10Z |
publishDate | 2023-11-01 |
publisher | Wiley |
record_format | Article |
series | IET Intelligent Transport Systems |
spelling | doaj.art-a5e154f8b9734a2e9c73d76eab2c89082023-11-17T05:48:56ZengWileyIET Intelligent Transport Systems1751-956X1751-95782023-11-0117112300231210.1049/itr2.12411Traffic speed prediction using GARCH‐GRU hybrid modelMuhammad Ali0Kamaludin Mohamad Yusof1Benjamin Wilson2Carina Ziegelmueller3School of Electrical Engineering Universiti Teknologi Malaysia Skudai JohorMalaysiaSchool of Electrical Engineering Universiti Teknologi Malaysia Skudai JohorMalaysiaHERE Technologies VictoriaAustraliaMichael Bauer International GmbH KarlsruheGermanyAbstract Traffic speed prediction is an integral part of an intelligent transportation system (ITS) because an advanced knowledge of traffic speed can help taking proactive preventive steps to avoid impending problems and it can also help in trip planning. Traffic speed data comprises a time series that may be modelled using any statistical or machine learning technique. In most of the cases, however, the performance of such models is bottlenecked due to heteroskedasticity usually present in such datasets. ARCH/GARCH family of models are generally used to model variance in such data. This paper presents a novel technique, termed as GARCH‐GRU, based on additive decomposition that splits data into random (residual) and deterministic parts. Random part is normalized using rolling standard deviation. GARCH (1, 1) is used to predict conditional variance of the residual and the predicted variance is then used in the basic model equation along with normalized residual that mimic white noise as required by the model. The data other than residual is modelled using a GRU model. The approach is applied to two datasets corresponding to a downtown road and a motorway. For comparison, the same datasets are exposed to three classical techniques; seasonal ARIMA, CNN and GRU techniques. The results demonstrate that the GARCH‐GRU technique outperforms others for random data of downtown road but fails to handle dynamic variations present in the motorway data.https://doi.org/10.1049/itr2.12411big dataintelligent transportation systems |
spellingShingle | Muhammad Ali Kamaludin Mohamad Yusof Benjamin Wilson Carina Ziegelmueller Traffic speed prediction using GARCH‐GRU hybrid model IET Intelligent Transport Systems big data intelligent transportation systems |
title | Traffic speed prediction using GARCH‐GRU hybrid model |
title_full | Traffic speed prediction using GARCH‐GRU hybrid model |
title_fullStr | Traffic speed prediction using GARCH‐GRU hybrid model |
title_full_unstemmed | Traffic speed prediction using GARCH‐GRU hybrid model |
title_short | Traffic speed prediction using GARCH‐GRU hybrid model |
title_sort | traffic speed prediction using garch gru hybrid model |
topic | big data intelligent transportation systems |
url | https://doi.org/10.1049/itr2.12411 |
work_keys_str_mv | AT muhammadali trafficspeedpredictionusinggarchgruhybridmodel AT kamaludinmohamadyusof trafficspeedpredictionusinggarchgruhybridmodel AT benjaminwilson trafficspeedpredictionusinggarchgruhybridmodel AT carinaziegelmueller trafficspeedpredictionusinggarchgruhybridmodel |