Using Degree Constrained Gravity Null-Models to understand the structure of journeys' networks in Bicycle Sharing Systems

Abstract : Bicycle Sharing Systems are now ubiquitous in large cities around the world. In most of these systems, journeys' data can be extracted , providing rich information to better understand it. Recent works have used network based-machine learning, and in particular space-corrected node clustering, to analyse such datasets. In this paper, we show that spatial-null models used in previous methods have a systematic bias, and we propose a degree-contrained null-model to improve the results. We finally apply the proposed method on the BSS of a city.
Liste complète des métadonnées

Cited literature [12 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01500352
Contributor : Lionel Tabourier <>
Submitted on : Monday, April 3, 2017 - 10:43:30 AM
Last modification on : Thursday, March 21, 2019 - 1:20:54 PM
Document(s) archivé(s) le : Tuesday, July 4, 2017 - 12:40:22 PM

File

nullSpatialModel1.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01500352, version 1

Citation

Rémy Cazabet, Pierre Borgnat, Pablo Jensen. Using Degree Constrained Gravity Null-Models to understand the structure of journeys' networks in Bicycle Sharing Systems. ESANN 2017 - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2017, Bruges, Belgium. ⟨hal-01500352⟩

Share

Metrics

Record views

267

Files downloads

123