When And Where Next: Individual Mobility Prediction
2012 (English)Conference paper (Refereed)
The ability to predict when an individual mobile user will leave his current location and where we will move next enables a myriad of qualitatively different Location-Based Services (LBSes) and applications. To this extent, the present paper proposes a statistical method that explicitly performs these related temporal and spatial prediction tasks in three continuous, sequential phases. In the First phase, the method continuously extracts grid-based staytime statistics from the GPS coordinate stream of the location-aware mobile device of the user. In the second phase, from the grid-based staytime statistics, the method periodically extracts and manages regions that the user frequently visits. Finally, in the third phase, from the stream of region-visits, the method continuously estimates parameters for an inhomogeneous continuous-time Markov model and in a continuous fashion predicts when the user will leave his current region and where he will move next. Empirical evaluations, using a number of long, real world trajectories from the Geo-Life data set, show that the proposed method outperforms a state-of-the-art, rule-based trajectory predictor both in terms of temporal and spatial prediction accuracy.
Place, publisher, year, edition, pages
ACM Press, 2012.
spatio-temporal data mining, mobility patterns, location prediction, inhomogeneous continuous-time Markov model
IdentifiersURN: urn:nbn:se:kth:diva-103247DOI: 10.1145/2442810.2442821ScopusID: 2-s2.0-84875182068OAI: oai:DiVA.org:kth-103247DiVA: diva2:559258
MobiGIS 2012 The First ACM SIGSPATIAL International Workshop on Mobile Geographical Information Systems, November 6, 2012, Redondo Beach, CA, USA
QC 201211132012-11-132012-10-082013-10-11Bibliographically approved