TY - GEN
T1 - Understanding Mobility Dynamics and Predicting Urban Traffic State via Improved Unsupervised Learning
AU - Wang, Ruiyi
AU - Tan, Huachun
AU - Ding, Fan
AU - Wen, Zoutao
N1 - Publisher Copyright:
© ASCE.
PY - 2023
Y1 - 2023
N2 - Traffic dynamic evolution concerning multiple coupling factors. The key to traffic forecasting is to deal with the multi-modal coupling spatiotemporal factors in the observation data, such as weather information (temperature, wind), different time scales (hours, days, weeks), and some uncontrollable random factors (traffic accidents, etc.). To this end, this paper proposes the semantic factorization-based traffic prediction generative adversarial network (SFTPGAN), which is an improved semantic factorization method based on unsupervised learning. It can automatically find meaningful semantic information in traffic dynamics evolution through its network structure and visualize the impact of each factor on the traffic dynamics evolution by changing the direction of each semantic individually. We evaluate the model on a large-scale GPS trajectory data set in the main urban area of Beijing and find it works well in searching semantic information.
AB - Traffic dynamic evolution concerning multiple coupling factors. The key to traffic forecasting is to deal with the multi-modal coupling spatiotemporal factors in the observation data, such as weather information (temperature, wind), different time scales (hours, days, weeks), and some uncontrollable random factors (traffic accidents, etc.). To this end, this paper proposes the semantic factorization-based traffic prediction generative adversarial network (SFTPGAN), which is an improved semantic factorization method based on unsupervised learning. It can automatically find meaningful semantic information in traffic dynamics evolution through its network structure and visualize the impact of each factor on the traffic dynamics evolution by changing the direction of each semantic individually. We evaluate the model on a large-scale GPS trajectory data set in the main urban area of Beijing and find it works well in searching semantic information.
UR - http://www.scopus.com/inward/record.url?scp=85173992660&partnerID=8YFLogxK
U2 - 10.1061/9780784484869.086
DO - 10.1061/9780784484869.086
M3 - Conference contribution
AN - SCOPUS:85173992660
T3 - CICTP 2023: Innovation-Empowered Technology for Sustainable, Intelligent, Decarbonized, and Connected Transportation - Proceedings of the 23rd COTA International Conference of Transportation Professionals
SP - 891
EP - 901
BT - CICTP 2023
A2 - Chen, Yanyan
A2 - Ma, Jianming
A2 - Zhang, Guohui
A2 - Wang, Haizhong
A2 - Sun, Lijun
A2 - He, Zhengbing
PB - American Society of Civil Engineers (ASCE)
T2 - 23rd COTA International Conference of Transportation Professionals: Innovation-Empowered Technology for Sustainable, Intelligent, Decarbonized, and Connected Transportation, CICTP 2023
Y2 - 14 July 2023 through 17 July 2023
ER -
