Recently, free floating bike sharing (FFBS) has become prevalent in China because of its convenience, sustainability, and energy savings. FFBS can be obtained and parked at any available place, unlimited by docking stations. However, traffic chaos caused by unbalanced allocation and disorderly parking has emerged. Accurate FFBS traffic pattern exploration is key to active traffic management. Large-scale travel records and online points of interests (POIs) in Shanghai are collected. Using these data, 3,325 FFBS gathering areas are discovered and six typical categories of land use are extracted by clustering analysis. Latent Dirichlet allocation (LDA) is conducted to discover latent FFBS travel patterns, and typical travel patterns are discussed in temporal and spatial characteristics. Results show huge differences in travel patterns between weekdays and weekends, and arrival times during the day are unevenly distributed. The research results are beneficial for reasonable resource allocation and helpful for accurate FFBS traffic management.
Exploring Free Floating Bike Sharing Travel Patterns Using Travel Records and Online Point of Interests
20th COTA International Conference of Transportation Professionals ; 2020 ; Xi’an, China (Conference Cancelled)
CICTP 2020 ; 2758-2769
2020-08-12
Conference paper
Electronic Resource
English
Method for Exploring Travel Routes Based on Cycle Ports in Bike-Sharing System
Springer Verlag | 2022
|Predicting travel demand of a bike sharing system using graph convolutional neural networks
Springer Verlag | 2025
|