Measuring the Relationship between Influence Factor and Urban Rail Transit Passenger Flow: Correlation or Causality?

Lu, Wenbo; Zhang, Yong; Ma, Chaoqun; Zhou, Bojian; Wang, Ting

doi:10.1061/(asce)up.1943-5444.0000870

Cited by 6 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang Yuping et al analyzed the influence mechanism and influence degree of changes in land use along the line, traffic connection, rail transit service level, and fare policy on urban rail transit passenger traffic and found that the passenger flow of a single rail transit line develops more slowly at the initial stage, and the cultivation period is longer [10]. Lu et al put forward a new method based on transfer information entropy (TIE), which is an indicator for the future long-term evaluation of the rail transit entropy (TIE) causal inference method used to determine the causal relationship between influencing factors and rail transit passenger flow, which can be used to derive the interaction between influencing factors and passenger flow after comparing with correlation analysis [11]. After analyzing passenger traffic and its influencing mechanism, various scholars have established models to predict the passenger flow.…”

Section: Introductionmentioning

confidence: 99%

Improved Long-Term Forecasting of Passenger Flow at Rail Transit Stations Based on an Artificial Neural Network

Du,

Yang,

Yin

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

When new rail stations or lines are planned, long-term planning for decades to come is required. The short-term passenger flow prediction is no longer of practical significance, as it only takes a few factors that affect passenger flow into consideration. To overcome this problem, we propose several long-term factors affecting the passenger flow of rail transit in this paper. We also create a visual analysis of these factors using ArcGIS and construct a long-term passenger flow prediction model for rail transit based on a class neural network using an SPSS Modeler. After optimizing relevant parameters, the prediction accuracy reaches 94.6%. We compare the results with other models and find that the neural network model has a good performance in predicting long-term rail transit passenger flow. Finally, the factors affecting passenger flow are ranked in terms of importance. It is found that among these factors, bicycles available for connection have the biggest influence on the passenger flow of rail stations.

show abstract

Section: Introductionmentioning

confidence: 99%