TY - GEN
T1 - An Informer-based Spatio-Temporal network for traffic flow forecasting
AU - Feng, Qi
AU - Wan, Kaifang
AU - Gao, Xiaoguang
AU - Evgeny, Neretin
AU - Li, Jinliang
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Spatio-temporal data is one type of multivariate time series(MTS), which has strong time dependence and complex spatial correlation. Spatio-temporal data prediction requires mining the temporal-spatial relations implied in the data to obtain trends in the data as they change over time and space. Traffic flow is a typical class of spatio-temporal data, due to the complexity of the traffic road network, the high spatio-temporal correlation of road conditions, and the strong coupling of traffic information in time and space, which makes it much more difficult to mine the correlation of data from traffic flow. However, existing traffic flow forecasting methods often focus only on its temporal attributes leading to the loss of spatial information or can only effectively handle short-time data, To solve this problem, we propose a spatio-temporal data network, which uses Informer to process the masked spatio-temporal data to enhance its data mining capability, and subsequently using spatio-temporal graph neural network (STGNN)to complete the spatial data processing. In this way, we achieve effective processing of long-time data. Finally, after the experimental validation on public dataset, the forecasting error of the proposed model is reduced and the training speed is improved.
AB - Spatio-temporal data is one type of multivariate time series(MTS), which has strong time dependence and complex spatial correlation. Spatio-temporal data prediction requires mining the temporal-spatial relations implied in the data to obtain trends in the data as they change over time and space. Traffic flow is a typical class of spatio-temporal data, due to the complexity of the traffic road network, the high spatio-temporal correlation of road conditions, and the strong coupling of traffic information in time and space, which makes it much more difficult to mine the correlation of data from traffic flow. However, existing traffic flow forecasting methods often focus only on its temporal attributes leading to the loss of spatial information or can only effectively handle short-time data, To solve this problem, we propose a spatio-temporal data network, which uses Informer to process the masked spatio-temporal data to enhance its data mining capability, and subsequently using spatio-temporal graph neural network (STGNN)to complete the spatial data processing. In this way, we achieve effective processing of long-time data. Finally, after the experimental validation on public dataset, the forecasting error of the proposed model is reduced and the training speed is improved.
KW - Informer
KW - Input mask
KW - Spatio-temporal data forecasting
KW - STGNNs
UR - http://www.scopus.com/inward/record.url?scp=85179000801&partnerID=8YFLogxK
U2 - 10.1109/ICCSI58851.2023.10304056
DO - 10.1109/ICCSI58851.2023.10304056
M3 - 会议稿件
AN - SCOPUS:85179000801
T3 - ICCSI 2023 - 2023 International Conference on Cyber-Physical Social Intelligence
SP - 532
EP - 537
BT - ICCSI 2023 - 2023 International Conference on Cyber-Physical Social Intelligence
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 International Conference on Cyber-Physical Social Intelligence, ICCSI 2023
Y2 - 20 October 2023 through 23 October 2023
ER -