Traffic Flow Online Prediction Based on a Generative Adversarial Network with Multi-Source Data

Traffic prediction is essential for advanced traffic planning, design, management, and network sustainability. Current prediction methods are mostly offline, which fail to capture the real-time variation of traffic flows. This paper establishes a sustainable online generative adversarial network (GA...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Tuo Sun, Bo Sun, Zehao Jiang, Ruochen Hao, Jiemin Xie
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	traffic flow prediction long short-term memory convolutional neural network improved generating adversarial network rolling time domain multi-dimensional indicators Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/e47cb2e205de4e02832f6869a1831cc9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e47cb2e205de4e02832f6869a1831cc9
record_format	dspace
spelling	oai:doaj.org-article:e47cb2e205de4e02832f6869a1831cc92021-11-11T19:46:59ZTraffic Flow Online Prediction Based on a Generative Adversarial Network with Multi-Source Data10.3390/su1321121882071-1050https://doaj.org/article/e47cb2e205de4e02832f6869a1831cc92021-11-01T00:00:00Zhttps://www.mdpi.com/2071-1050/13/21/12188https://doaj.org/toc/2071-1050Traffic prediction is essential for advanced traffic planning, design, management, and network sustainability. Current prediction methods are mostly offline, which fail to capture the real-time variation of traffic flows. This paper establishes a sustainable online generative adversarial network (GAN) by combining bidirectional long short-term memory (BiLSTM) and a convolutional neural network (CNN) as the generative model and discriminative model, respectively, to keep learning with continuous feedback. BiLSTM constantly generates temporal candidate flows based on valuable memory units, and CNN screens out the best spatial prediction by returning the feedback gradient to BiLSTM. Multi-dimensional indicators are selected to map the multi-view fusion local trend for accurate prediction. To balance computing efficiency and accuracy, different batch sizes are pre-tested and allocated to different lanes. The models are trained with rectified adaptive moment estimation (RAdam) by dividing the dataset into the training and testing sets with a rolling time-domain scheme. In comparison with the autoregressive integrated moving average (ARIMA), BiLSTM, generating adversarial network for traffic flow (GAN-TF), and generating adversarial network for non-signal traffic (GAN-NST), the proposed improved generating adversarial network for traffic flow (IGAN-TF) successfully generates more accurate and stable flows and performs better.Tuo SunBo SunZehao JiangRuochen HaoJiemin XieMDPI AGarticletraffic flow predictionlong short-term memoryconvolutional neural networkimproved generating adversarial networkrolling time domainmulti-dimensional indicatorsEnvironmental effects of industries and plantsTD194-195Renewable energy sourcesTJ807-830Environmental sciencesGE1-350ENSustainability, Vol 13, Iss 12188, p 12188 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	traffic flow prediction long short-term memory convolutional neural network improved generating adversarial network rolling time domain multi-dimensional indicators Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350
spellingShingle	traffic flow prediction long short-term memory convolutional neural network improved generating adversarial network rolling time domain multi-dimensional indicators Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350 Tuo Sun Bo Sun Zehao Jiang Ruochen Hao Jiemin Xie Traffic Flow Online Prediction Based on a Generative Adversarial Network with Multi-Source Data
description	Traffic prediction is essential for advanced traffic planning, design, management, and network sustainability. Current prediction methods are mostly offline, which fail to capture the real-time variation of traffic flows. This paper establishes a sustainable online generative adversarial network (GAN) by combining bidirectional long short-term memory (BiLSTM) and a convolutional neural network (CNN) as the generative model and discriminative model, respectively, to keep learning with continuous feedback. BiLSTM constantly generates temporal candidate flows based on valuable memory units, and CNN screens out the best spatial prediction by returning the feedback gradient to BiLSTM. Multi-dimensional indicators are selected to map the multi-view fusion local trend for accurate prediction. To balance computing efficiency and accuracy, different batch sizes are pre-tested and allocated to different lanes. The models are trained with rectified adaptive moment estimation (RAdam) by dividing the dataset into the training and testing sets with a rolling time-domain scheme. In comparison with the autoregressive integrated moving average (ARIMA), BiLSTM, generating adversarial network for traffic flow (GAN-TF), and generating adversarial network for non-signal traffic (GAN-NST), the proposed improved generating adversarial network for traffic flow (IGAN-TF) successfully generates more accurate and stable flows and performs better.
format	article
author	Tuo Sun Bo Sun Zehao Jiang Ruochen Hao Jiemin Xie
author_facet	Tuo Sun Bo Sun Zehao Jiang Ruochen Hao Jiemin Xie
author_sort	Tuo Sun
title	Traffic Flow Online Prediction Based on a Generative Adversarial Network with Multi-Source Data
title_short	Traffic Flow Online Prediction Based on a Generative Adversarial Network with Multi-Source Data
title_full	Traffic Flow Online Prediction Based on a Generative Adversarial Network with Multi-Source Data
title_fullStr	Traffic Flow Online Prediction Based on a Generative Adversarial Network with Multi-Source Data
title_full_unstemmed	Traffic Flow Online Prediction Based on a Generative Adversarial Network with Multi-Source Data
title_sort	traffic flow online prediction based on a generative adversarial network with multi-source data
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/e47cb2e205de4e02832f6869a1831cc9
work_keys_str_mv	AT tuosun trafficflowonlinepredictionbasedonagenerativeadversarialnetworkwithmultisourcedata AT bosun trafficflowonlinepredictionbasedonagenerativeadversarialnetworkwithmultisourcedata AT zehaojiang trafficflowonlinepredictionbasedonagenerativeadversarialnetworkwithmultisourcedata AT ruochenhao trafficflowonlinepredictionbasedonagenerativeadversarialnetworkwithmultisourcedata AT jieminxie trafficflowonlinepredictionbasedonagenerativeadversarialnetworkwithmultisourcedata
_version_	1718431441405083648

Traffic Flow Online Prediction Based on a Generative Adversarial Network with Multi-Source Data

Ejemplares similares