文献类型：期刊文献

英文题名：FDSA-STG: Fully Dynamic Self-Attention Spatio-Temporal Graph Networks for Intelligent Traffic Flow Prediction

作者：Duan, Youxiang[1,2];Chen, Ning[1,2];Shen, Shigen[3];Zhang, Peiying[1,2];Qu, Youyang[4];Yu, Shui[5]

机构：[1]China Univ Petr East China, Coll Comp Sci & Technol, Qingdao 266580, Peoples R China;[2]Xidian Univ, State Key Lab Integrated Serv Networks, Xian 710071, Peoples R China;[3]Shaoxing Univ, Dept Comp Sci & Engn, Shaoxing 312000, Peoples R China;[4]Australia Commonwealth Sci & Ind Res Org, Data61, Canberra, ACT 2601, Australia;[5]Univ Technol Sydney, Sch Comp Sci, Ultimo, NSW 2007, Australia

年份：2022

卷号：71

期号：9

起止页码：9250

外文期刊名：IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY

收录：SCI-EXPANDED(收录号：WOS:000854658600013)、、EI(收录号：20224112866725)、Scopus(收录号：2-s2.0-85137416037)、WOS

基金：This work was supported in part by the Shandong Provincial Natural Science Foundation, China under Grant ZR2020MF006, in part by the Industry-University Research Innovation Foundation of Ministry of Education of China under Grant 2021FNA01001, in part by theMajor Scientific and Technological Projects of CNPC under Grant ZD2019-183-006, in part by the Open Foundation of State Key Laboratory of Integrated Services Networks (Xidian University) underGrant ISN23-09, and in part by the Zhejiang Provincial Natural Science Foundation of China under Grant LZ22F020002.

语种：英文

外文关键词：Vehicle dynamics; Correlation; Feature extraction; Deep learning; Transportation; Time series analysis; Data mining; Deep learning (DL); graph attention networks (GATs); intelligent transportation systems (ITS); self-attention; traffic flow prediction (TFP)

外文摘要：With the development of transportation and the ever-improving of vehicular technology, Artificial Intelligence (AI) has been popularized in Intelligent Transportation Systems (ITS), especially in Traffic Flow Prediction (TFP). TFP plays an increasingly important role in alleviating traffic pressure caused by regional emergencies and coordinating resource allocation in advance to deployment decisions. However, existing research can hardly model the original intricate structural relationships of the transportation network (TN) due to the lack of in-depth consideration of the dynamic relevance of spatial, temporal, and periodic characteristics. Motivated by this and combined with deep learning (DL), we propose a novel framework entitled Fully Dynamic Self-Attention Spatio-Temporal Graph Networks (FDSA-STG) by improving the attention mechanism using Graph Attention Networks (GATs). In particular, to dynamically integrate the correlations of spatial dimension, time dimension, and periodic characteristics for highly-accurate prediction, we correspondingly devised three components including the spatial graph attention component (SGAT), the temporal graph attention component (TGAT), and the fusion layer. In this case, three groups of similar structures are designed to extract the flow characteristics of recent periodicity, daily periodicity, and weekly periodicity. Extensive evaluation results show the superiority of FDSA-STG from perspectives of prediction accuracy and prediction stability improvements, which also testifies high model adaptability to the dynamic characteristics of the actual observed traffic flow (TF).