Exploiting Multiple Radii to Learn Significant Locations
Location contexts are important for many context-aware applications. A significant location is a specialized form of location context for expressing a user’s daily activity. We propose a method to cluster positions measured by cellular phones into significant locations with multiple radii. Cellular phones we used are equipped with a positioning system, where data can be taken in low frequency with wide-varying estimated errors. In order to learn significant locations, our system exploits multiple radii for coping with these characteristics and for adapting to a variety of users’ spatial behavioral patterns. We also discuss appropriate parameters for our clustering method.
KeywordsLocation Candidate Cellular Phone Spatial Behavior Threshold Density Ubiquitous Environment
Unable to display preview. Download preview PDF.
- 1.Ashbrook, D., Staner, T.: Learning Significant Locations and Predicting User Movement with GPS. In: Proceedings of the IEEE International Symposium on Wearable Computers, pp. 101–108 (2002)Google Scholar
- 4.Liao, L., Fox, D., Kautz, H.: Learning and inferring transportation routines. In: Proceedings of the National Conference on Artificial Intelligence, pp. 348–353 (2004)Google Scholar
- 6.gpsOne, http://www.cdmatech.com/
- 7.Java 2 Platform, Micro Edition (J2ME) Sun Microsystems, http://java.sun.com/j2me/
- 8.Brickley, D., et al.: GeoOnion ESW Wiki, http://esw.w3.org/topic/GeoOnion