A Hybrid Model for Vessel Traffic Flow Prediction Based on Wavelet and Prophet

Accurate vessel traffic flow prediction is significant for maritime traffic guidance and control. According to the characteristics of vessel traffic flow data, a new hybrid model, named DWT–Prophet, is proposed based on the discrete wavelet decomposition and Prophet framework for the prediction of v...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Dangli Wang, Yangran Meng, Shuzhe Chen, Cheng Xie, Zhao Liu
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/88e7be3ae24241a5a8fa4775afed3482
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:88e7be3ae24241a5a8fa4775afed3482
record_format dspace
spelling oai:doaj.org-article:88e7be3ae24241a5a8fa4775afed34822021-11-25T18:04:33ZA Hybrid Model for Vessel Traffic Flow Prediction Based on Wavelet and Prophet10.3390/jmse91112312077-1312https://doaj.org/article/88e7be3ae24241a5a8fa4775afed34822021-11-01T00:00:00Zhttps://www.mdpi.com/2077-1312/9/11/1231https://doaj.org/toc/2077-1312Accurate vessel traffic flow prediction is significant for maritime traffic guidance and control. According to the characteristics of vessel traffic flow data, a new hybrid model, named DWT–Prophet, is proposed based on the discrete wavelet decomposition and Prophet framework for the prediction of vessel traffic flow. First, vessel traffic flow was decomposed into a low-frequency component and several high-frequency components by wavelet decomposition. Second, Prophet was trained to predict the components, respectively. Finally, the prediction results of the components were reconstructed to complete the prediction. The experimental results demonstrate that the hybrid DWT–Prophet outperformed the single Prophet, long short-term memory, random forest, and support vector regression (SVR). Moreover, the practicability of the new forecasting method was improved effectively.Dangli WangYangran MengShuzhe ChenCheng XieZhao LiuMDPI AGarticlevessel traffic flowpredictionwavelet decompositionProphetNaval architecture. Shipbuilding. Marine engineeringVM1-989OceanographyGC1-1581ENJournal of Marine Science and Engineering, Vol 9, Iss 1231, p 1231 (2021)
institution DOAJ
collection DOAJ
language EN
topic vessel traffic flow
prediction
wavelet decomposition
Prophet
Naval architecture. Shipbuilding. Marine engineering
VM1-989
Oceanography
GC1-1581
spellingShingle vessel traffic flow
prediction
wavelet decomposition
Prophet
Naval architecture. Shipbuilding. Marine engineering
VM1-989
Oceanography
GC1-1581
Dangli Wang
Yangran Meng
Shuzhe Chen
Cheng Xie
Zhao Liu
A Hybrid Model for Vessel Traffic Flow Prediction Based on Wavelet and Prophet
description Accurate vessel traffic flow prediction is significant for maritime traffic guidance and control. According to the characteristics of vessel traffic flow data, a new hybrid model, named DWT–Prophet, is proposed based on the discrete wavelet decomposition and Prophet framework for the prediction of vessel traffic flow. First, vessel traffic flow was decomposed into a low-frequency component and several high-frequency components by wavelet decomposition. Second, Prophet was trained to predict the components, respectively. Finally, the prediction results of the components were reconstructed to complete the prediction. The experimental results demonstrate that the hybrid DWT–Prophet outperformed the single Prophet, long short-term memory, random forest, and support vector regression (SVR). Moreover, the practicability of the new forecasting method was improved effectively.
format article
author Dangli Wang
Yangran Meng
Shuzhe Chen
Cheng Xie
Zhao Liu
author_facet Dangli Wang
Yangran Meng
Shuzhe Chen
Cheng Xie
Zhao Liu
author_sort Dangli Wang
title A Hybrid Model for Vessel Traffic Flow Prediction Based on Wavelet and Prophet
title_short A Hybrid Model for Vessel Traffic Flow Prediction Based on Wavelet and Prophet
title_full A Hybrid Model for Vessel Traffic Flow Prediction Based on Wavelet and Prophet
title_fullStr A Hybrid Model for Vessel Traffic Flow Prediction Based on Wavelet and Prophet
title_full_unstemmed A Hybrid Model for Vessel Traffic Flow Prediction Based on Wavelet and Prophet
title_sort hybrid model for vessel traffic flow prediction based on wavelet and prophet
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/88e7be3ae24241a5a8fa4775afed3482
work_keys_str_mv AT dangliwang ahybridmodelforvesseltrafficflowpredictionbasedonwaveletandprophet
AT yangranmeng ahybridmodelforvesseltrafficflowpredictionbasedonwaveletandprophet
AT shuzhechen ahybridmodelforvesseltrafficflowpredictionbasedonwaveletandprophet
AT chengxie ahybridmodelforvesseltrafficflowpredictionbasedonwaveletandprophet
AT zhaoliu ahybridmodelforvesseltrafficflowpredictionbasedonwaveletandprophet
AT dangliwang hybridmodelforvesseltrafficflowpredictionbasedonwaveletandprophet
AT yangranmeng hybridmodelforvesseltrafficflowpredictionbasedonwaveletandprophet
AT shuzhechen hybridmodelforvesseltrafficflowpredictionbasedonwaveletandprophet
AT chengxie hybridmodelforvesseltrafficflowpredictionbasedonwaveletandprophet
AT zhaoliu hybridmodelforvesseltrafficflowpredictionbasedonwaveletandprophet
_version_ 1718411691924914176