Tracking the evolution of temporal patterns of usage in bicycle-sharing systems using nonnegative matrix factorization on multiple sliding windows

Bicycle-Sharing Systems (BSS) are growing quickly in popularity all over the world. In this article, the authors propose a method based on Nonnegative Matrix Factorization to study the typical temporal patterns of usage of the BSS of Lyon, France, by studying logs of rentals. First, the authors show how this approach allows them to understand the spatial and temporal usage of the system. Second, the authors show how they can track the evolution of these temporal patterns over several years, and how this information can be used to better understand the BSS, but also changes in the city itself, by considering the stations as social sensors.

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01673828
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Jun 9 2018 3:00PM