Abstract
With the advantages of convenient access and free parking, urban dockless shared bikes are favored by the public. However, the irregular flow of dockless shared bikes poses a challenge for the research of flow pattern. In this paper, the flow characteristics of dockless shared bikes are expounded through the analysis of the time series location data of ofo and mobike shared bikes in Beijing. Based on the analysis, a model called DestiFlow is proposed to describe the spatio-temporal flow of urban dockless shared bikes based on points of interest (POIs) clustering. The results show that the DestiFlow model can find the aggregation areas of dockless shared bikes and describe the structural characteristics of the flow network. Our model can not only predict the demand for dockless shared bikes, but also help to grasp the mobility characteristics of citizens and improve the urban traffic management system.
Highlights
Shared bikes are the products of the shared economy and the development of the Internet of things
The flow characteristics of dockless shared bikes are expounded through the analysis of the time series location data of ofo and mobike shared bikes in Beijing
A model called DestiFlow is proposed to describe the spatio-temporal flow of urban dockless shared bikes
Summary
Shared bikes are the products of the shared economy and the development of the Internet of things. Liu et al used the method of deep learning to infer the distribution of dockless shared bikes in a new city [15] These studies are based on the regular geographic grid, and the dockless shared bikes are assigned to corresponding grids according to their locations. A model called DestiFlow is proposed to describe the spatio-temporal flow of urban dockless shared bikes. The POI-based clustering is used to find the aggregation areas of dockless shared bikes, this method avoids the problems of regular geographic grid method effectively. On the basis of the aggregation areas, the spatial distribution model of dockless shared bikes is constructed according to the characteristics of flow distance and the activity of each aggregation area. The third section proposes the spatio-temporal flow model of urban dockless shared bikes based on POIs clustering called DestiFlow. The fifth section carries on a case analysis and the sixth section gives the summarization of the paper
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
