Predicting Destination Station in Real Time Based on Public Transit Passenger Profiling

The smart card is an universal tool in public transit. It collects large amounts of data on buses, urban railway transit, and ferries, and provides opportunities for passenger profiling. Such advanced data collection, processing, and learning tools provide a foundation for efficiently analyzing and predicting real-time travel behavior and demand. To this end, the contribution this study makes is combining offline analysis of passenger profiling with real-time prediction to propose a method that accurately predicts the destination station in real time when passengers swipe their smart travel cards (“tag on”), First, a static database of transit passenger profiling was constructed, having identified dual passenger travel patterns based on Density-Based Spatial Clustering of Applications with Noise. The transit passenger profiling included origin–destination-time- and destination-time travel characteristics. A rapid real-time prediction algorithm based on transit passenger profiling and Roulette Wheel Selection (RWS) was proposed, to predict the destination of boarding passengers. Rules were set to distinguish between regular and irregular passengers: passenger profiling was applied to regular passengers, and RWS to irregular passengers. This study provides a technical foundation for real-time passenger-flow prediction, monitoring, and simulation, and prediction of short-term passenger behavior and demand. Furthermore, it facilitates efficient, real-time acquisition of passengers’ travel destinations and demand. To validate its practical performance, an actual case simulation was conducted, yielding an accuracy rate of 80.27% during peak hours and maintaining 70.07% overall. These results demonstrate both the technical feasibility and operational efficiency of the proposed solution.

Authors

Institutions

Publication Details

Journal
Transportation Research Record Journal of the Transportation Research Board
Published
2026-11-20
DOI
https://doi.org/10.1177/03611981261491299
Primary Topic
Transportation Planning and Optimization
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Predicting Destination Station in Real Time Based on Public Transit Passenger Profiling

Fangsheng Wang, Xuyang Song, Ruihua Xu, Minh Kieu et al.
1 links
Transportation Research Record Journal of the Transportation Research Board
Transportation Planning and Optimization
article

Predicting Destination Station in Real Time Based on Public Transit Passenger Profiling

Fangsheng Wang, Xuyang Song, Ruihua Xu, Minh Kieu, Jun Yin, Wenjun Li
article en

Abstract

The smart card is an universal tool in public transit. It collects large amounts of data on buses, urban railway transit, and ferries, and provides opportunities for passenger profiling. Such advanced data collection, processing, and learning tools provide a foundation for efficiently analyzing and predicting real-time travel behavior and demand. To this end, the contribution this study makes is combining offline analysis of passenger profiling with real-time prediction to propose a method that accurately predicts the destination station in real time when passengers swipe their smart travel cards (“tag on”), First, a static database of transit passenger profiling was constructed, having identified dual passenger travel patterns based on Density-Based Spatial Clustering of Applications with Noise. The transit passenger profiling included origin–destination-time- and destination-time travel characteristics. A rapid real-time prediction algorithm based on transit passenger profiling and Roulette Wheel Selection (RWS) was proposed, to predict the destination of boarding passengers. Rules were set to distinguish between regular and irregular passengers: passenger profiling was applied to regular passengers, and RWS to irregular passengers. This study provides a technical foundation for real-time passenger-flow prediction, monitoring, and simulation, and prediction of short-term passenger behavior and demand. Furthermore, it facilitates efficient, real-time acquisition of passengers’ travel destinations and demand. To validate its practical performance, an actual case simulation was conducted, yielding an accuracy rate of 80.27% during peak hours and maintaining 70.07% overall. These results demonstrate both the technical feasibility and operational efficiency of the proposed solution.

Transportation Research Record Journal of the Transportation Research Board
Tongji University (CN), Shanghai University of Engineering Science (CN), University of Auckland (NZ)
Sustainable cities and communities, Industry, innovation and infrastructure
Transportation Planning and Optimization
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon