Deep spatio-temporal 3D dilated dense neural network for traffic flow prediction

作者全名："He, Rui; Zhang, Cuijuan; Xiao, Yunpeng; Lu, Xingyu; Zhang, Song; Liu, Yanbing"

作者地址："[He, Rui; Xiao, Yunpeng; Lu, Xingyu; Zhang, Song; Liu, Yanbing] Chongqing Univ Posts & Telecommun, Coll Comp Sci & Technol, Chongqing 400065, Peoples R China; [Liu, Yanbing] Chongqing Med Univ, Chongqing 400016, Peoples R China; [Zhang, Cuijuan] Anqing Normal Univ, Key Lab Intelligent Percept & Comp Anhui Prov, Anqing 246133, Peoples R China"

通信作者："Liu, YB (通讯作者)，Chongqing Univ Posts & Telecommun, Coll Comp Sci & Technol, Chongqing 400065, Peoples R China.; Liu, YB (通讯作者)，Chongqing Med Univ, Chongqing 400016, Peoples R China."

来源：EXPERT SYSTEMS WITH APPLICATIONS

ESI学科分类：ENGINEERING

WOS号：WOS:001079147700001

JCR分区：Q1

影响因子：7.5

年份：2024

卷号：237

期号：　

开始页：　

结束页：　

文献类型：Article

关键词：Deep learning; Traffic prediction; 3D convolutional neural network; 3D dilated convolution; Multi-scale dilated densenet network; Trajectory data

摘要："Traffic flow prediction is increasingly vital for the administration of metropolitan areas. Many research on spatio-temporal networks have been explored but the impacts of both spatial and temporal flexibility, complex spatial correlation has not been considered simultaneously. We present the Spatio-Temporal 3D Multiscale Dilated Dense Network (ST-3DMDDN), a novel 3D Convolutional Neural Network (3DCNN) deep learning neural network for the road level and region level traffic flow prediction. It uses autocorrelation analysis' early fusion method for importance sampling, a 3D multiscale dilated convolutional network to capture nearby and remote correlations simultaneously, and a densely connected network for deeper feature extraction. Considering traffic flow's heterogeneity, a new block called the ""Spatial and Channel Recalibrate""(SCR) is designed to accurately analyze the correlation contributions. The ST-3DMDDN model is evaluated using three real traffic flows, and the findings indicate that our approach surpasses the performance of the baseline approaches."

基金机构："National Natural Science Foundation of China [61772098, 62272074]; Chongqing Postgraduate Research and Innovation Project [CYB22241]; Anhui Provincial Research Programming Project [2022AH05 1039]"

基金资助正文："This work is supported by the National Natural Science Foundation of China (Project No. 61772098, No. 62272074) , Chongqing Postgraduate Research and Innovation Project under Grant CYB22241, Anhui Provincial Research Programming Project under Grant No. 2022AH05 1039."