City-wide urban infrastructures are increasingly reliant on networked technology to improve and expand their services. As a side effect of this digitalization, large amounts of data can be sensed and analyzed to uncover patterns of human behavior. These digital footprints have implications for city planners and the citizens that live or visit those cities. To highlight the potential of such datasets, we focus on digital footprints from one type of urban infrastructure: shared bicycling systems. We provide a spatio-temporal analysis of six weeks of bicycle station usage data from Barcelona's shared bicycling system called Bicing. Using a combination of clustering and statistical machine learning techniques (Bayesian Networks), we show how these digital trace can be used to uncover and predict behaviors. We apply clustering techniques to identify shared behaviors across stations and explore how those behaviors relate to location, neighborhood and time of day. We then show how Bayesian Networks can be used to model and predict station usage.
Figure 1 (a) A nearly full Bicing station; (b) A station kiosk; (c) A close-up of a locked bicycle; (d) A map of Barcelona showing the location of the 373 Bicing stations. The five highlighted stations are discussed below.
Figure 2. (a) The clustering results; (b) A scatterplot of station elevation vs. average number of available bicycles.
"Sensing and Predicting the Pulse of the City through Shared Bicycling" Froehlich, J., Neumann, J., and Oliver, N. (2009) Twenty-First International Joint Conference on Artificial Intelligence (IJCAI-09), Pasadena, California, USA, July 11 - 17, 2009.
Acceptance Rate: 25.7% (331/1290)
"Measuring the Pulse of the City through Shared Bicycle Programs" Froehlich, J., Neumann, J., and Oliver, N. (2008) International Workshop on Urban, Community, and Social Applications of Networked Sensing Systems - UrbanSense08, Raleigh, North Carolina, USA, November 4, 2008
"Telefonica develops solutions for Bicing". El Pais Newspaper. Oct 2008
"Telefonica works on 3D video and social shopping". Expansion Newspaper. Oct 2008
"Telefonica predicts that the mobile phone will be used to do social shopping". Expansion Newspaper. Oct 2008