The primary objective of this study is to predict the short-term demand of free-floating bike sharing (FFBS) using deep learning approach. The FFBS trip data in Shanghai city are collected from the Mobike Company. Other datasets such as weather data and air quality data are also collected. The spatiotemporal patterns of FFBS demand indicates that the weekday rides exhibit an obvious commuting pattern while the weekend rides are usually involved with various trip purposes. Then, a hybrid deep learning neural network (HDL-net) is developed to predict the short-term FFBS demand for different time intervals including 15, 20 and 30 min. The proposed HDL-net exhibits better performance on morning peak than the evening peak and non-peak hours for all the three time intervals. Moreover, five benchmark methods are also used to compare with the proposed HDL-net. The results suggest that the proposed hybrid deep learning framework outperform the benchmarks in the prediction performance for all three time intervals. The results of this study could provide insightful suggestions for transportation authorities to develop effective rebalancing strategies and bike lanes planning schemes to promote the service level of cycling in an urban city.
Short-term FFBS demand prediction with multi-source data in a hybrid deep learning framework
IET Intelligent Transport Systems ; 13 , 9 ; 1340-1347
2019-05-20
8 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
spatiotemporal patterns , weekday rides , FFBS trip data , convolutional neural nets , multisource data , hybrid deep learning framework , learning (artificial intelligence) , artificial neural network , morning peak , HDL-net exhibits better performance , autoregressive moving average processes , air quality data , road traffic , prediction performance , hourly aggregated weather data , short-term travel demand , Shanghai city , weekend rides , transportation , nonpeak hours , short-term FFBS demand prediction , bike-sharing service provider , bicycles , hybrid deep learning neural network , commuting pattern , evening peak , convolutional neural network , deep learning approach , short-term memory , recurrent neural nets , regression analysis , bike lanes , free-floating bike sharing
Metadata by IET is licensed under CC BY 3.0
Short‐term FFBS demand prediction with multi‐source data in a hybrid deep learning framework
Wiley | 2019
|Deep learning for short-term traffic flow prediction
Elsevier | 2017
|