Hup-me: inferring and reconciling a timeline of user activity from rich smartphone data

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.

[1]  Nando de Freitas,et al.  An Introduction to Sequential Monte Carlo Methods , 2001, Sequential Monte Carlo Methods in Practice.

[2]  Michel Bierlaire,et al.  Probabilistic Multimodal Map Matching With Rich Smartphone Data , 2015, J. Intell. Transp. Syst..

[3]  Thad Starner,et al.  Using GPS to learn significant locations and predict movement across multiple users , 2003, Personal and Ubiquitous Computing.

[4]  Henry A. Kautz,et al.  Learning and inferring transportation routines , 2004, Artif. Intell..

[5]  Patrick Weber,et al.  OpenStreetMap: User-Generated Street Maps , 2008, IEEE Pervasive Computing.

[6]  Robert B. Noland,et al.  Current map-matching algorithms for transport applications: State-of-the art and future research directions , 2007 .

[7]  Michael L. Littman,et al.  Activity Recognition from Accelerometer Data , 2005, AAAI.

[8]  Gary M. Weiss,et al.  Activity recognition using cell phone accelerometers , 2011, SKDD.

[9]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[10]  Nando de Freitas,et al.  Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks , 2000, UAI.

[11]  Philip S. Yu,et al.  Transportation mode detection using mobile phones and GIS information , 2011, GIS.

[12]  Alexandre M. Bayen,et al.  The Path Inference Filter: Model-Based Low-Latency Map Matching of Probe Vehicle Data , 2011, IEEE Transactions on Intelligent Transportation Systems.

[13]  Stuart J. Russell,et al.  Dynamic bayesian networks: representation, inference and learning , 2002 .

[14]  Deborah Estrin,et al.  Using mobile phones to determine transportation modes , 2010, TOSN.

[15]  James Biagioni,et al.  Cooperative transit tracking using smart-phones , 2010, SenSys '10.

[16]  Freda Kemp,et al.  An Introduction to Sequential Monte Carlo Methods , 2003 .

[17]  Sasu Tarkoma,et al.  Accelerometer-based transportation mode detection on smartphones , 2013, SenSys '13.

[18]  Ling Bao,et al.  Activity Recognition from User-Annotated Acceleration Data , 2004, Pervasive.

[19]  N. Gordon,et al.  Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[20]  Xing Xie,et al.  Understanding transportation modes based on GPS data for web applications , 2010, TWEB.

[21]  Sivan Toledo,et al.  VTrack: accurate, energy-aware road traffic delay estimation using mobile phones , 2009, SenSys '09.

[22]  John Krumm,et al.  Hidden Markov map matching through noise and sparseness , 2009, GIS.

[23]  Jian Ma,et al.  Accelerometer Based Transportation Mode Recognition on Mobile Phones , 2010, 2010 Asia-Pacific Conference on Wearable Computing Systems.

[24]  Johannes Peltola,et al.  Activity classification using realistic data from wearable sensors , 2006, IEEE Transactions on Information Technology in Biomedicine.

[25]  Daniel P. Siewiorek,et al.  Activity recognition and monitoring using multiple sensors on different body positions , 2006, International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06).

[26]  James Biagioni,et al.  EasyTracker: automatic transit tracking, mapping, and arrival time prediction using smartphones , 2011, SenSys.

[27]  Chengyang Zhang,et al.  Map-matching for low-sampling-rate GPS trajectories , 2009, GIS.

[28]  Sebastian Thrun,et al.  Probabilistic robotics , 2002, CACM.