A Traffic Congestion Prediction Model Based on Dilated-Dense Network

When using the convolutional neural network (CNN) model to predict short-term traffic congestion, due to the convolution pooling operation of the model, part of the data for the information of the target position will be lost, resulting in the decline of the resolution of the output features and the...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	SHI Min, CAI Shaowei, YI Qingming
Formato:	article
Lenguaje:	ZH
Publicado:	Editorial Office of Journal of Shanghai Jiao Tong University 2021
Materias:	dilated-dense network spatio-temporal characteristics convolutional neural networks short-term traffic congestion prediction Engineering (General). Civil engineering (General) TA1-2040 Chemical engineering TP155-156 Naval architecture. Shipbuilding. Marine engineering VM1-989
Acceso en línea:	https://doaj.org/article/72c08a795cb84eb6a76afa1b54d9a739
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:72c08a795cb84eb6a76afa1b54d9a739
record_format	dspace
spelling	oai:doaj.org-article:72c08a795cb84eb6a76afa1b54d9a7392021-11-04T09:34:25ZA Traffic Congestion Prediction Model Based on Dilated-Dense Network1006-246710.16183/j.cnki.jsjtu.2020.99.009https://doaj.org/article/72c08a795cb84eb6a76afa1b54d9a7392021-02-01T00:00:00Zhttp://xuebao.sjtu.edu.cn/CN/10.16183/j.cnki.jsjtu.2020.99.009https://doaj.org/toc/1006-2467When using the convolutional neural network (CNN) model to predict short-term traffic congestion, due to the convolution pooling operation of the model, part of the data for the information of the target position will be lost, resulting in the decline of the resolution of the output features and the decrease in the predictive ability of the model. To solve this problem, this paper proposes a dilated-dense neural network model. First, it uses dilated convolution to obtain the characteristics of a larger receptive field with fewer network parameters, and fully extracts complex and variable data spatio-temporal characteristics. Then, through down-sampling and equivalent mapping of dense network, it solves the problem of parameter degradation in the process of increasing layers of neural network. Finally, it uses the actual urban road average speed data blocks to verify the validity of the model. The results show that compared with the convolutional neural network model, the average absolute error of the network structure prediction is reduced by 3% to 23%.SHI MinCAI ShaoweiYI QingmingEditorial Office of Journal of Shanghai Jiao Tong Universityarticledilated-dense networkspatio-temporal characteristicsconvolutional neural networksshort-term traffic congestion predictionEngineering (General). Civil engineering (General)TA1-2040Chemical engineeringTP155-156Naval architecture. Shipbuilding. Marine engineeringVM1-989ZHShanghai Jiaotong Daxue xuebao, Vol 55, Iss 02, Pp 124-130 (2021)
institution	DOAJ
collection	DOAJ
language	ZH
topic	dilated-dense network spatio-temporal characteristics convolutional neural networks short-term traffic congestion prediction Engineering (General). Civil engineering (General) TA1-2040 Chemical engineering TP155-156 Naval architecture. Shipbuilding. Marine engineering VM1-989
spellingShingle	dilated-dense network spatio-temporal characteristics convolutional neural networks short-term traffic congestion prediction Engineering (General). Civil engineering (General) TA1-2040 Chemical engineering TP155-156 Naval architecture. Shipbuilding. Marine engineering VM1-989 SHI Min CAI Shaowei YI Qingming A Traffic Congestion Prediction Model Based on Dilated-Dense Network
description	When using the convolutional neural network (CNN) model to predict short-term traffic congestion, due to the convolution pooling operation of the model, part of the data for the information of the target position will be lost, resulting in the decline of the resolution of the output features and the decrease in the predictive ability of the model. To solve this problem, this paper proposes a dilated-dense neural network model. First, it uses dilated convolution to obtain the characteristics of a larger receptive field with fewer network parameters, and fully extracts complex and variable data spatio-temporal characteristics. Then, through down-sampling and equivalent mapping of dense network, it solves the problem of parameter degradation in the process of increasing layers of neural network. Finally, it uses the actual urban road average speed data blocks to verify the validity of the model. The results show that compared with the convolutional neural network model, the average absolute error of the network structure prediction is reduced by 3% to 23%.
format	article
author	SHI Min CAI Shaowei YI Qingming
author_facet	SHI Min CAI Shaowei YI Qingming
author_sort	SHI Min
title	A Traffic Congestion Prediction Model Based on Dilated-Dense Network
title_short	A Traffic Congestion Prediction Model Based on Dilated-Dense Network
title_full	A Traffic Congestion Prediction Model Based on Dilated-Dense Network
title_fullStr	A Traffic Congestion Prediction Model Based on Dilated-Dense Network
title_full_unstemmed	A Traffic Congestion Prediction Model Based on Dilated-Dense Network
title_sort	traffic congestion prediction model based on dilated-dense network
publisher	Editorial Office of Journal of Shanghai Jiao Tong University
publishDate	2021
url	https://doaj.org/article/72c08a795cb84eb6a76afa1b54d9a739
work_keys_str_mv	AT shimin atrafficcongestionpredictionmodelbasedondilateddensenetwork AT caishaowei atrafficcongestionpredictionmodelbasedondilateddensenetwork AT yiqingming atrafficcongestionpredictionmodelbasedondilateddensenetwork AT shimin trafficcongestionpredictionmodelbasedondilateddensenetwork AT caishaowei trafficcongestionpredictionmodelbasedondilateddensenetwork AT yiqingming trafficcongestionpredictionmodelbasedondilateddensenetwork
_version_	1718444968697135104

A Traffic Congestion Prediction Model Based on Dilated-Dense Network

Ejemplares similares