Skip to Main content Skip to Navigation
New interface
Conference papers

Hup-Me: Inferring and Reconciling a Timeline of User Activity with Smartphone and Personal Data

Abstract : We designed a system to infer multimodal itineraries traveled by a user from a combination of smartphone sensor data (e.g., GPS, Wi-Fi, accelerometer) and knowledge of the transport network infrastructure (e.g., road and rail maps, public transportation timetables). The system uses a Transportation network that captures the set of possible paths of this network for the modes, e.g., foot, bicycle, road_vehicle, and rail. This Transportation network is constructed from OpenStreetMap data and public transportation routes published online by transportation agencies in GTFS format. The system infers itineraries from a sequence of smartphone observations in two phases. The first phase uses a dynamic Bayesian network that models the probabilistic relationship between paths in Transportation network and sensor data. The second phase attempts to match portions recognized as road_vehicle or rail with possible public transportation routes of type bus, train, metro, or tram extracted from the GTFS source. We evaluated the performance of our system with data from users traveling over the Paris area who were asked to record data for different trips via an Android application. Itineraries were annotated with modes and public transportation routes taken and we report on the results of the recognition.
Document type :
Conference papers
Complete list of metadata
Contributor : Admin Télécom Paristech Connect in order to contact the contributor
Submitted on : Tuesday, January 26, 2016 - 9:16:57 AM
Last modification on : Friday, February 4, 2022 - 3:22:14 AM


  • HAL Id : hal-01261964, version 1


David Montoya, Serge Abiteboul, Pierre Senellart. Hup-Me: Inferring and Reconciling a Timeline of User Activity with Smartphone and Personal Data. SIGSPATIAL (Special Interest Group on Spatial Information), Nov 2015, Seattle, United States. ⟨hal-01261964⟩



Record views