Station layout and scheduling optimization could improve public bicycle system efficiency, and it is important to analyze and forecast the spatial and temporal distribution of demand. Based on rental data of the Hohhot public bicycle system in 2017, this study establishes a public bicycle demand forecasting model using back propagation (BP) neural network. A station with large demand is selected to analyze the distribution of demand in different periods. By analyzing the similarity of data in different periods, the law of data variation is determined. Then the public bicycle demand forecasting model based on BP neural network (PBDF-BP model) is trained and validated by using peak hour rental data. By comparing the prediction accuracy with other forecasting models, it is found that the PBDF-BP model has less error in prediction results and higher stability. These findings may be help promote the sustainable development of public bicycle systems.
Research on Public Bicycle Demand Forecasting Based on Historical Data and BP Neural Network
20th COTA International Conference of Transportation Professionals ; 2020 ; Xi’an, China (Conference Cancelled)
CICTP 2020 ; 3074-3086
2020-12-09
Conference paper
Electronic Resource
English
Public Bicycle Prediction Based on Generalized Regression Neural Network
British Library Conference Proceedings | 2015
|