The Community for Technology Leaders
Green Image
Issue No. 01 - Jan.-Mar. (2017 vol. 16)
ISSN: 1536-1268
pp: 66-73
Ian Craig , University of New South Wales
Mark Whitty , University of New South Wales
As low-power devices continue to be integrated into daily life, we are presented with the challenge of deciding when it's beneficial for these devices to interrupt us. Predicting a user's movements provides valuable insight to solve this problem. Here, the authors present a new approach for offline location prediction for low-power devices, representing a user's mobility patterns as an optimal set of geographical regions. Their approach yielded a 27 percent increase in precision and a 13 percent increase in recall over standard time- and place-based approaches against GPS data for hundreds of users. Their approach requires minimal additional cost and opens up potential for further development.
Urban areas, Prediction algorithms, Pervasive computing, Computational modeling, Privacy, Global Positioning System, Mobile radio mobility management, Data analysis, Context-aware services,context-aware computing, location prediction, route prediction, geographic regions, merging, mobile, pervasive computing, data analysis
Ian Craig, Mark Whitty, "Region Formation for Efficient Offline Location Prediction", IEEE Pervasive Computing, vol. 16, no. , pp. 66-73, Jan.-Mar. 2017, doi:10.1109/MPRV.2017.13
86 ms
(Ver 3.3 (11022016))