Title :
A spatio-temporal forecasting method of railway passenger flow
Author :
Xu, Wei ; Huang, Hou-Kuan ; Qin, Yong
Author_Institution :
Sch. of Comput. & Inf. Technol., Beijing Jiaotong Univ., China
Abstract :
In this paper, some key methods to forecast passenger flow are thoroughly studied and analyzed. A new method of such forecasting based on spatio-temporal data mining is also introduced and presented. Such a new method can forecast complex data with both spatial and temporal attributes. The effectiveness of this approach has been validated by the genuine data collected from Chinese railway system. It also shows an improved forecasting accuracy and an enhanced stability.
Keywords :
data mining; forecasting theory; railways; sensor fusion; spatiotemporal phenomena; Chinese railway system; railway passenger flow forecasting; sensor fusion; spatiotemporal data mining; spatiotemporal forecasting method; Cities and towns; Data mining; Demand forecasting; Gravity; Hip; Neural networks; Predictive models; Rail transportation; Telecommunication traffic; Traffic control;
Conference_Titel :
Machine Learning and Cybernetics, 2004. Proceedings of 2004 International Conference on
Print_ISBN :
0-7803-8403-2
DOI :
10.1109/ICMLC.2004.1382020
