Prediction of Station Passenger Flow Volume Based on Fractal Theory

Abstract

In order to seek the distribution rule of station passenger flow and discuss research methods of public transport based on station, prediction model of station passenger flow volume was proposed with the fractal theory. Firstly, it used correlation dimension to establish a time series forecasting model, which analyzes the time distribution rule of station passenger flow with the phase space reconstruction theory. Finally, it took the stations of Route 255 in Changchun as example, which used the time series forecasting model to forecast the station passenger flow volume at moments. It is shown that the model obtains a less error and a greater application value.

Mixed logit model based on nonlinear random utility functions: A transfer passenger demand prediction method on overnight D-trains

“…(b) The time series analysis methods are based on the time which is seen as the independent variable, to establish passenger flow prediction models, such as Wang et al (2012) and Yin et al (2017). There are also some models which can be combined with time series methods, for example, seasonal model, such as Tian et al (2011) and Guang et al (2017); grey model, such as Li et al (2007) and Huang et al (2014); neural network model, such as Chen et al (2001), Dia (2001), Stella et al (2006), Eleni (2007), Eleni et al (2010), Wei et al (2012), Li et al (2014), Glišović et al (2016) and Ivanov et al (2018); and MD model, such as Wang et al (2017).…”