ST-3DGMR: Spatio-temporal 3D grouped multiscale ResNet network for region-based urban traffic flow prediction

作者全名："He, Rui; 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"

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

来源：INFORMATION SCIENCES

ESI学科分类：COMPUTER SCIENCE

WOS号：WOS:000915590400001

JCR分区：Q1

影响因子：8.1

年份：2023

卷号：624

期号：　

开始页：68

结束页：93

文献类型：Article

关键词：Flow prediction; Spatio-temporal data; Multiscale network; 3D convolution neural networks; Dilated convolution

摘要："Predicting urban flow is crucial for intelligent transportation systems (ITS), but it is not easy due to several complicated elements (such as dynamic spatio-temporal dependencies, complex spatial dependence, external environment, and so on). Some studies utilize LSTM and 2D CNN networks to analyze temporal and spatial relationships independently, do not fully model spatio-temporal dependence or multiscale spatial dependence among regions. Inspired by the similarity of video analysis, we propose a new pure spatio-temporal model based on 3D convolutional neural network (3DCNN) to simultaneously capture spatiotemporal features from low-level to high-level layers, and design a grouped 3D multiscale residual strategy to directly and effectively extract multiscale spatial features. Based on these, we propose the Spatio-Temporal 3D Grouped Multiscale ResNet (ST-3DGMR), an end-to-end framework for region-based urban flow prediction. By adaptively integrating closeness and periodic spatio-temporal 3DCNN branches as well as other external factors, the ST-3DGMR can forecast future region-based inflow and outflow. To assess the performance of the proposed method, we use three representative traffic datasets. When compared to state-of-the-art techniques, experimental results show that the ST-3DGMR can lower RMSE by 2.6 %, 6.3 %, and 6.9 % on the BikeNYC, TaxiBJ, and TaxiCQ datasets, respectively.(c) 2022 Published by Elsevier Inc."

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

基金资助正文："This work is supported by the Chongqing Postgraduate Research and Innovation Project under Grant CYB22241. National Natural Science Foundation of China (Grant No.61772098,No.62272074) . The authors sincerely thank Xu ZHANG, Associate Professor in Chongqing University of Posts and Telecommunications for collecting the TaxiCQ datasets."