01475693

Component

This paper proposes an intelligence-based approach to predicting passengers’ route choice behaviour, which is crucial to the effective utilisation of transportation stations. Although intelligence-based model (e.g., artificial neural network) have been developed rapidly and widely adopted in various fields in the last few decades, their application to predict human decision-making in pedestrian flows is limited, as the actual route choice decisions of passengers involve human behaviour. A comprehensive methodology for capturing route choice behaviour is still lacking, because extensive labour and time resources are required to collect passenger movement data from different stations. In this study, a four-month site-survey was carried out to collect actual route choice behaviour information in nine transportation stations in Hong Kong during peak hours by following passengers and recording their chosen route. The authors developed an intelligent model to capture passengers’ route choice decision-making that achieved a prediction accuracy of almost 88% and this intelligent model is proposed to implement in the simulation tools for passenger flow simulation.

This paper was sponsored by TRB committee ANF10 Pedestrians.

01470560

13-1134

English

20p

2013

Transportation Research Board 92nd Annual Meeting

Digital/other

Figures; References; Tables

Mathematical prediction; Neural networks; Peak periods; Pedestrian flow; Rail transit stations; Route choice; Surveying

Hong Kong (China)

Planning and Forecasting; Public Transportation; I72: Traffic and Transport Planning

Transportation Research Board Annual Meeting 2013 Paper #13-1134

TRIS, TRB, ATRI

Feb 5 2013 12:19PM