TY - GEN
T1 - K -STTN
T2 - 22nd IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2023
AU - Wan, Youjie
AU - Li, Jing
AU - Guo, Qi
AU - Peng, Yue
AU - Shi, Benyun
N1 - Funding Information:
This work was supported in part by the NSFC/RGC Joint Research Scheme (No. 62261160387, N HKBU222/22), and the General Research Fund of Hong Kong (Nos. RGC/HKBU12202220 and RGC/HKBU12203122).
Publisher Copyright:
© 2023 IEEE.
PY - 2023/10/26
Y1 - 2023/10/26
N2 - Accurate traffic forecasting is essential to improve traffic efficiency, ensure urban traffic safety, and promote sus-tainable urban development. In recent years, extensive deep-learning methods have been proposed to deal with the highly nonlinear and dynamic spatio-temporal dependencies in traffic forecasting problems. However, few of them have considered the underlying correlations between different traffic factors, such as the correlation between traffic flow and speed. Based on knowledge derived from the field of transportation, in this paper, we propose a knowledge-induced spatio-temporal transformer Network (K-STTN) to simultaneously forecast both traffic flow and speed. By introducing Greenshields' traffic model in a spatio-temporal transformer network, we aim to automatically investigate both spatio-temporal dependencies and flow-speed correlations in an end-to-end learning manner. To evaluate the performance of the proposed K-STTN model, we conduct exper-iments on two California highway public datasets (i.e., PeMS04 and PeMS08). Experimental results show that the K-STTN model outperforms the state-of-the-art baseline models in terms of forecasting accuracy. In summary, the practice of knowledge-induced neural networks in this paper offers new insights into the design of neural networks by integrating knowledge from specific domains.
AB - Accurate traffic forecasting is essential to improve traffic efficiency, ensure urban traffic safety, and promote sus-tainable urban development. In recent years, extensive deep-learning methods have been proposed to deal with the highly nonlinear and dynamic spatio-temporal dependencies in traffic forecasting problems. However, few of them have considered the underlying correlations between different traffic factors, such as the correlation between traffic flow and speed. Based on knowledge derived from the field of transportation, in this paper, we propose a knowledge-induced spatio-temporal transformer Network (K-STTN) to simultaneously forecast both traffic flow and speed. By introducing Greenshields' traffic model in a spatio-temporal transformer network, we aim to automatically investigate both spatio-temporal dependencies and flow-speed correlations in an end-to-end learning manner. To evaluate the performance of the proposed K-STTN model, we conduct exper-iments on two California highway public datasets (i.e., PeMS04 and PeMS08). Experimental results show that the K-STTN model outperforms the state-of-the-art baseline models in terms of forecasting accuracy. In summary, the practice of knowledge-induced neural networks in this paper offers new insights into the design of neural networks by integrating knowledge from specific domains.
KW - Greenshields' traffic model
KW - Spatio-temporal dependencies
KW - Spatio-temporal transformer networks
KW - Traffic forecasting
UR - http://www.scopus.com/inward/record.url?scp=85182523902&partnerID=8YFLogxK
U2 - 10.1109/WI-IAT59888.2023.00093
DO - 10.1109/WI-IAT59888.2023.00093
M3 - Conference proceeding
AN - SCOPUS:85182523902
SN - 9798350309195
T3 - IEEE WIC ACM International Conference on Web Intelligence (WI)
SP - 563
EP - 568
BT - Proceedings - 2023 22nd IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2023
A2 - Gurrola, Javier
PB - IEEE
Y2 - 26 October 2023 through 29 October 2023
ER -
