Inferring bike trip patterns from bike sharing system open data - Archive ouverte HAL Accéder directement au contenu
Poster De Conférence Année : 2015

Inferring bike trip patterns from bike sharing system open data

Résumé

Understanding bike trip patterns in a bike sharing system is important for researchers designing models for station placement and bike scheduling. By bike trip patterns, we refer to the large number of bike trips observed between two stations. However, due to privacy and operational concerns, bike trip data are usually not made publicly available. In this paper, instead of relying on time-consuming surveys and inaccurate simulations, we attempt to infer bike trip patterns directly from station status data, which are usually public to help riders find nearby stations and bikes. However, the station status data do not contain information about where the bikes come from and go to, therefore the same observations on stations might correspond to different underlying bike trips. To address this challenge, We conduct an empirical study on a sample bike trip dataset to gain insights about the inner structure of bike trips. We then formulate the trip inference problem as an ill-posed inverse problem, and propose a regularization technique to incorporate the a priori information about bike trips to solve the problem. We evaluate our method using real-world bike sharing datasets from Washington, D.C. Results show that our method effectively infers bike trip patterns
Fichier non déposé

Dates et versions

hal-01270577 , version 1 (08-02-2016)

Identifiants

Citer

Longbiao Chen, Jérémie Jakubowicz. Inferring bike trip patterns from bike sharing system open data. BIGDATA 2015 : International Conference on Big Data, Oct 2015, Santa Clara, États-Unis. IEEE, pp.2898 - 2900 2015, ⟨10.1109/BigData.2015.7364115⟩. ⟨hal-01270577⟩
54 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More