A Data-driven Framework for Bike-sharing Data Analytics

Authors: Shaohua Wang*, ASU, Xiayi Zhang, ASU, Wenwen Li, ASU, Qingren Jia, ASU
Topics: Geographic Information Science and Systems, Human-Environment Geography, Geographic Information Science and Systems
Keywords: Share-ride Bicycles, Trajectory Analysis, Spatial Clustering, Shortest Path Algorithm, Map-Matching
Session Type: Paper
Day: 4/4/2019
Start / End Time: 5:00 PM / 6:40 PM
Room: Roosevelt 0, Marriott, Exhibition Level
Presentation File: No File Uploaded

Understanding bike mobility patterns is important for transportation management, city planning, and share economy activities. In this study, we propose a data-driven framework to support the spatiotemporal analytics of bike-sharing data. This framework is implemented in a geographic information systems environment to facilitate integration with multi-source geospatial data, including Points of Interest(POI) and multi-modal transportation networks (roads, bike lanes, public transit and metro). The world’s largest bike-share city, Shanghai, China, serves as our study area. The spatial, temporal, network and travel behavior characteristics are explored, including trip distribution analysis, space-time hotspots of bike use, the popularity of road segments and trip route patterns. The research findings can be applied in bike lanes planning, bike trip management and human activity-travel rescheduling.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login