The application of space-time ARIMA model on traffic flow forecasting

• Published in: 2009 International Conference on Machine Learning and Cybernetics Vol. 6; pp. 3408 - 3412
• Main Authors: Shu-Lan Lin, Hong-Qiong Huang, Da-Qi Zhu, Tian-Zhen Wang
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.07.2009
• Subjects: Constraint theory; Cybernetics; Data engineering; Educational institutions; Forecasting; Intelligent Transport Systems; Machine learning; Predictive models; Random variables; STARIMA; Telecommunication traffic; Traffic control; Traffic flow network; Vectors
• DOI: 10.1109/ICMLC.2009.5212785
• ISBN: 9781424437023; 1424437024
• ISSN: 2160-133X

Traffic flow data are in the form of spatial time series and are collected at specific locations at constant intervals of time. Space-time autoregressive time series modeling is a promising inductive method that uses a small number of parameters and can be used for online monitoring and prediction. In this paper, we develop space-time autoregressive models for urban traffic flow network scenarios. We evaluate the ability of the space-time autoregressive models to model the spatial and temporal correlations in the traffic network and show that the space-time model performs well.