Breadcrumbs: A Feature Rich Mobility Dataset with Point of Interest Annotation

In this paper, we present Breadcrumbs, a mobility dataset collected in the city of Lausanne (Switzerland) from multiple mobile phone sensors (GPS, WiFi, Bluetooth) from 81 users for a duration of 12 weeks. Currently available mobility datasets are restricted to geospatial information obtained through a single sensor at low spatiotemporal granularities. Furthermore, this passively collected data lacks ground-truth information regarding points of interest and their semantic labels. These features are critical in order to push the possibilities of geospatial data analysis towards analyzing mobility behaviors and movement patterns at a fine-grained scale. To this end, Breadcrumbs provides ground-truth and semantic labels for the points of interest of all the participants. The dataset also contains fine-grained demographic attributes, contact records, calendar events and social relationship tags between the participants. In order to demonstrate the significance of the ground-truth annotations, we discuss several use cases of this dataset. Furthermore, we compare four contrasting and widely used unsupervised clustering approaches for point of interest extraction from geolocation trajectories. Using the ground-truth information, we perform a detailed performance validation of these techniques and highlight their strengths and weaknesses. Given that mobility data is derived from an individuals inherent need of participating in activities, narrowing the gap between raw trajectory data points and complete trip annotation in essential. We thus make Breadcrumbs accessible to the research community in order to facilitate research in the direction of supervised human mobility learning schemes.

[1]  J. A. Hartigan,et al.  A k-means clustering algorithm , 1979 .

[2]  Christophe Diot,et al.  CRAWDAD dataset thlab/sigcomm2009 (v.2012-07-15) , 2012 .

[3]  F. Oswald,et al.  The use of advanced tracking technologies for the analysis of mobility in Alzheimer's disease and related cognitive diseases , 2008, BMC geriatrics.

[4]  Jiawei Han,et al.  Mining periodic behaviors for moving objects , 2010, KDD.

[5]  Benoît Garbinato,et al.  Extracting Hotspots without A-priori by Enabling Signal Processing over Geospatial Data , 2017, SIGSPATIAL/GIS.

[6]  Benoît Garbinato,et al.  MobiDict: a mobility prediction system leveraging realtime location data streams , 2016, IWGS@SIGSPATIAL.

[7]  Benoît Garbinato,et al.  Capturing complex behaviour for predicting distant future trajectories , 2016, MobiGIS.

[8]  Depeng Jin,et al.  Walking Without Friends: Publishing Anonymized Trajectory Dataset Without Leaking Social Relationships , 2019, IEEE Transactions on Network and Service Management.

[9]  Sébastien Gambs,et al.  Differential Privacy Models for Location-Based Services , 2016, Trans. Data Priv..

[10]  Christian Poellabauer,et al.  Hierarchical Cooperative Discovery of Personal Places from Location Traces , 2018, IEEE Transactions on Mobile Computing.

[11]  Yanmin Zhu,et al.  A GPU-Accelerated Framework for Processing Trajectory Queries , 2018, 2018 IEEE 34th International Conference on Data Engineering (ICDE).

[12]  Le Gruenwald,et al.  Towards an Efficient Top-K Trajectory Similarity Query Processing Algorithm for Big Trajectory Data on GPGPUs , 2016, 2016 IEEE International Congress on Big Data (BigData Congress).

[13]  Daqing Zhang,et al.  Fine-grained preference-aware location search leveraging crowdsourced digital footprints from LBSNs , 2013, UbiComp.

[14]  Hervé Rivano,et al.  PRIVA'MOV: Analysing Human Mobility Through Multi-Sensor Datasets , 2017 .

[15]  Liang Liu,et al.  Estimating Origin-Destination Flows Using Mobile Phone Location Data , 2011, IEEE Pervasive Computing.

[16]  W. Bruce Croft,et al.  Predicting query performance , 2002, SIGIR '02.

[17]  James Irvine,et al.  Nodobo: Mobile Phone as a Software Sensor for Social Network Research , 2011, 2011 IEEE 73rd Vehicular Technology Conference (VTC Spring).

[18]  Ciprian Dobre,et al.  CRAWDAD dataset upb/hyccups (v.2016-10-17) , 2016 .

[19]  D. Gática-Pérez,et al.  Towards rich mobile phone datasets: Lausanne data collection campaign , 2010 .

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

[21]  Albert-László Barabási,et al.  The origin of bursts and heavy tails in human dynamics , 2005, Nature.

[22]  Tao Zhou,et al.  Diversity of individual mobility patterns and emergence of aggregated scaling laws , 2012, Scientific Reports.

[23]  Xiaoming Fu,et al.  Trajectory Recovery From Ash: User Privacy Is NOT Preserved in Aggregated Mobility Data , 2017, WWW.

[24]  Ralf Hartmut Güting,et al.  BerlinMOD: a benchmark for moving object databases , 2009, The VLDB Journal.

[25]  Shashi Shekhar,et al.  Discovering personal gazetteers: an interactive clustering approach , 2004, GIS '04.

[26]  Nathan Griffiths,et al.  Identifying locations from geospatial trajectories , 2016, J. Comput. Syst. Sci..

[27]  Benoît Garbinato,et al.  A Location Privacy Estimator Based on Spatio-Temporal Location Uncertainties , 2017, NETYS.

[28]  Sébastien Gambs,et al.  Show me how you move and I will tell you who you are , 2010, SPRINGL '10.

[29]  Alex Pentland,et al.  Once Upon a Crime: Towards Crime Prediction from Demographics and Mobile Data , 2014, ICMI.

[30]  Jean-Yves Le Boudec,et al.  Quantifying Location Privacy , 2011, 2011 IEEE Symposium on Security and Privacy.

[31]  Benoît Garbinato,et al.  Discovering demographic data of users from the evolution of their spatio-temporal entropy , 2018, ArXiv.

[32]  Nicholas Jing Yuan,et al.  You Are Where You Go: Inferring Demographic Attributes from Location Check-ins , 2015, WSDM.

[33]  Daniel Gatica-Perez,et al.  Discovering human places of interest from multimodal mobile phone data , 2010, MUM.

[34]  Daqing Zhang,et al.  Modeling User Activity Preference by Leveraging User Spatial Temporal Characteristics in LBSNs , 2015, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[35]  John D. Kelleher,et al.  Examining the Limits of Predictability of Human Mobility , 2019, Entropy.

[36]  Ehsan Kazemi,et al.  Been There, Done That: What Your Mobility Traces Reveal about Your Behavior , 2012 .

[37]  Michelle Pasquale Fillekes,et al.  Self-reported versus GPS-derived indicators of daily mobility in a sample of healthy older adults. , 2019, Social science & medicine.

[38]  Jignesh M. Patel,et al.  Indexing Large Trajectory Data Sets With SETI , 2003, CIDR.

[39]  Kyriakos Mouratidis,et al.  Efficient Motif Discovery in Spatial Trajectories Using Discrete Fréchet Distance , 2017, EDBT.

[40]  Mirco Musolesi,et al.  The Rise of People-Centric Sensing , 2008, IEEE Internet Comput..

[41]  Benoît Garbinato,et al.  Geodabs: Trajectory Indexing Meets Fingerprinting at Scale , 2018, 2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS).

[42]  Jing Tao,et al.  Inferring Demographics and Social Networks of Mobile Device Users on Campus From AP-Trajectories , 2017, WWW.

[43]  Alex Pentl,et al.  Reality Mining of Mobile Communications: Toward A New Deal On Data , 2009 .

[44]  Roberto Trasarti,et al.  Discovering and Understanding City Events with Big Data: The Case of Rome , 2017, Inf..

[45]  Li Tu,et al.  Density-based clustering for real-time stream data , 2007, KDD '07.

[46]  Kentaro Toyama,et al.  Project Lachesis: Parsing and Modeling Location Histories , 2004, GIScience.

[47]  Yang Zhang,et al.  walk2friends: Inferring Social Links from Mobility Profiles , 2017, CCS.

[48]  Marc-Olivier Killijian,et al.  Next place prediction using mobility Markov chains , 2012, MPM '12.

[49]  Tamara B Harris,et al.  Dog Ownership, Walking Behavior, and Maintained Mobility in Late Life , 2006, Journal of the American Geriatrics Society.

[50]  Michael Devetsikiotis,et al.  CRAWDAD dataset unm/blebeacon (v.2019-03-12) , 2019 .

[51]  Xing Xie,et al.  GeoLife: A Collaborative Social Networking Service among User, Location and Trajectory , 2010, IEEE Data Eng. Bull..

[52]  Alex Pentland,et al.  Reality mining: sensing complex social systems , 2006, Personal and Ubiquitous Computing.

[53]  Hugh F. Durrant-Whyte,et al.  Simultaneous Localization, Mapping and Moving Object Tracking , 2007, Int. J. Robotics Res..

[54]  Karl Aberer,et al.  Next Place Prediction using Mobile Data , 2012 .

[55]  Jure Leskovec,et al.  Friendship and mobility: user movement in location-based social networks , 2011, KDD.

[56]  Stefano Chessa,et al.  Mobile crowd sensing management with the ParticipAct living lab , 2017, Pervasive Mob. Comput..