@inproceedings{discovery10064493,
         journal = {Transportation Research Board 95th Annual Meeting},
           title = {A Forecasting Model of the Proportion of Peak-Period Boardings for Urban Mass Transit System: A Case Study of Osaka Prefecture},
            year = {2016},
       booktitle = {Proceedings of the Transportation Research Board 95th Annual Meeting},
       publisher = {National Academy of Sciences},
            note = {This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.},
           month = {January},
             url = {https://trid.trb.org/view/1393392},
          author = {Cheng, Y and Ye, X and Wang, Z},
        abstract = {At the planning and design phase of urban mass transit system, the aim is to grasp the features of spatial and temporal distributions of passenger flow during peak period. For this goal, dynamic passenger assignment model should be applied. An indispensable input parameter of this model is time-varying interstation OD matrix of peak period. To gaining this parameter, the first step is figuring out peak period boardings (excluding interchanges, PPB). Since all-day boardings can be extracted from the given all-day OD matrix, the study focuses on forecasting the proportion of PPB. Taking Osaka Prefecture as research area, this article firstly proposes a new concept of station catchment area as the border of data collection, which can be determined by two types of risks. With the help of Spearman correlation analysis, 3 factors prove to be significantly associated with the proportion of PPB. Then two regression models are conducted with socio-economic and land-use characteristics as independent variables respectively. Results show that the model with the proportion of resident population as independent variable has a better performance, of which the adjusted R2 17 reaches 0.951 and the standard error of verification data is only 7.8 percent.},
        keywords = {Urban Mass Transit, Peak Period, Proportion of Boardings, Two Types of Risks, Regression Model}
}