File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Multi-step-ahead traffic speed forecasting using multi-output gradient boosting regression tree

TitleMulti-step-ahead traffic speed forecasting using multi-output gradient boosting regression tree
Authors
KeywordsDirect strategy
iterated strategy
multivariate GBRT
multi-step-ahead prediction
traffic speed forecasting
Issue Date2020
PublisherTaylor & Francis Inc. The Journal's web site is located at http://www.tandf.co.uk/journals/titles/15472450.asp
Citation
Journal of Intelligent Transportation Systems, 2020, v. 24 n. 2, p. 125-141 How to Cite?
AbstractShort-term traffic speed forecasting is an important component of Intelligent Transportation Systems (ITS). Multi-step-ahead prediction can provide more information and predict the longer trend of traffic speed than single-step-ahead prediction. This paper presents a multi-step-ahead traffic speed prediction approach by improving the gradient boosting regression tree (GBRT). The traditional multiple output strategies, e.g., the direct strategy and iterated strategy, share a common feature that they model the samples through multi-input single-output mapping rather than multi-input multi-output mapping. This paper proposes multivariate GBRT to realize simultaneous multiple outputs by considering correlations of the outputs which have not been fully considered in the existing strategies. For illustrative purposes, traffic detection data are extracted at the 5-min aggregation time interval from three loop detectors in US101-N freeway through the Performance Measurement System (PeMS). The support vector regression (SVR) is used as the benchmark. Assessments on the three models are based on the three criteria, i.e., prediction accuracy, prediction stability, and prediction time. The results indicate that (I) Multivariate GBRT and GBRT using the direct strategy have higher prediction accuracies compared with SVR; (II) GBRT using the iterated strategy has a good prediction accuracy in short-step-ahead prediction and the prediction accuracy decreases significantly in long-step-ahead prediction; (III) Multivariate GBRT has the best stability which means the higher reliability in multi-step-ahead prediction while iterated GBRT has the worst stability; and (IV) Multivariate GBRT has an enormous advantage in the prediction efficiency and this advantage will expand with the increasing prediction horizons.
Persistent Identifierhttp://hdl.handle.net/10722/274852
ISSN
2017 Impact Factor: 2.164
2015 SCImago Journal Rankings: 1.774

 

DC FieldValueLanguage
dc.contributor.authorZhan, X-
dc.contributor.authorZhang, S-
dc.contributor.authorSzeto, WY-
dc.contributor.authorChen, X(M)-
dc.date.accessioned2019-09-10T02:30:12Z-
dc.date.available2019-09-10T02:30:12Z-
dc.date.issued2020-
dc.identifier.citationJournal of Intelligent Transportation Systems, 2020, v. 24 n. 2, p. 125-141-
dc.identifier.issn1547-2450-
dc.identifier.urihttp://hdl.handle.net/10722/274852-
dc.description.abstractShort-term traffic speed forecasting is an important component of Intelligent Transportation Systems (ITS). Multi-step-ahead prediction can provide more information and predict the longer trend of traffic speed than single-step-ahead prediction. This paper presents a multi-step-ahead traffic speed prediction approach by improving the gradient boosting regression tree (GBRT). The traditional multiple output strategies, e.g., the direct strategy and iterated strategy, share a common feature that they model the samples through multi-input single-output mapping rather than multi-input multi-output mapping. This paper proposes multivariate GBRT to realize simultaneous multiple outputs by considering correlations of the outputs which have not been fully considered in the existing strategies. For illustrative purposes, traffic detection data are extracted at the 5-min aggregation time interval from three loop detectors in US101-N freeway through the Performance Measurement System (PeMS). The support vector regression (SVR) is used as the benchmark. Assessments on the three models are based on the three criteria, i.e., prediction accuracy, prediction stability, and prediction time. The results indicate that (I) Multivariate GBRT and GBRT using the direct strategy have higher prediction accuracies compared with SVR; (II) GBRT using the iterated strategy has a good prediction accuracy in short-step-ahead prediction and the prediction accuracy decreases significantly in long-step-ahead prediction; (III) Multivariate GBRT has the best stability which means the higher reliability in multi-step-ahead prediction while iterated GBRT has the worst stability; and (IV) Multivariate GBRT has an enormous advantage in the prediction efficiency and this advantage will expand with the increasing prediction horizons.-
dc.languageeng-
dc.publisherTaylor & Francis Inc. The Journal's web site is located at http://www.tandf.co.uk/journals/titles/15472450.asp-
dc.relation.ispartofJournal of Intelligent Transportation Systems-
dc.rightsThis is an Accepted Manuscript of an article published by Taylor & Francis in Journal of Intelligent Transportation Systems on 18 Mar 2019, available online: http://www.tandfonline.com/10.1080/15472450.2019.1582950-
dc.subjectDirect strategy-
dc.subjectiterated strategy-
dc.subjectmultivariate GBRT-
dc.subjectmulti-step-ahead prediction-
dc.subjecttraffic speed forecasting-
dc.titleMulti-step-ahead traffic speed forecasting using multi-output gradient boosting regression tree-
dc.typeArticle-
dc.identifier.emailSzeto, WY: ceszeto@hku.hk-
dc.identifier.authoritySzeto, WY=rp01377-
dc.description.naturepostprint-
dc.identifier.doi10.1080/15472450.2019.1582950-
dc.identifier.hkuros303140-
dc.identifier.volume24-
dc.identifier.issue2-
dc.identifier.spage125-
dc.identifier.epage141-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats