The goal of this study was to assess the performance of two algorithms for using mobile GPS data to identify patterns in users' visits to stores, restaurants and other establishments. Over a 1-month period, subjects carried GPS data loggers when traveling in their local area, and made daily reports of their visits to establishments in a voicemail or email diary. The results showed lower accuracy in using GPS data to estimate durations of visits to larger buildings. However, when establishment categories were ranked by visit frequency and duration, the GPS-derived rankings matched those derived from the diary data at a level that was significantly greater than chance.
Get full access to this article
View all access options for this article.
References
1.
ChosetH.NagataniK.LazarN. A. (2003). The arc-transversal median algorithm: A geometric approach to increasing ultrasonic sensor azimuth accuracy. IEEE Transactions on Robotics & Automation, 19(3), 513–522.
2.
EagleN.PentlandA. (2006). Eigenbehaviors: Identifying structure in routine. Paper presented at the Ubicomp 1906, Orange County, California, USA.
3.
EsterM.KriegelH.-P.SanderJ.XuX. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. Paper presented at the 2nd International Conference on Knowledge Discovery and Data Mining, Menlo Park, California, USA.
4.
FarrahiK.Gatica-PerezD. (2008). Daily routine classification from mobile phone data. Paper presented at the 5th Joint Workshop on Machine Learning and Multimodal Interaction, Utrecht, The Netherlands.
5.
FroehlichJ.ChenM.SmithI.PotterF. (2006). Voting with your feet: An investigative study of the relationship between place visit behavior and preference. Paper presented at the UbiComp 2006, Orange County, CA.
HariharanR.ToyamaK. (2004). Parsing and modeling location histories. Paper presented at the International Conference on Geographic Information Science, Adelphi, Maryland, USA.
8.
KangJ. H.WelbourneW.StewartB.BorrielloG. (2004). Extracting places from traces of locations. Paper presented at the WMASH, Philadelphia, Pennsylvania, USA.
9.
KrulwichB. (1997). Lifestyle finder: Intelligent user profiling using large-scale demographic data. AI Magazine, 18(2), 37–45.
10.
LaasonenK.RaentoM.ToivonenH. (2004). Adaptive on-device location recognition. Paper presented at the PERVASIVE 2004, Vienna, Austria.
11.
MarmasseN.SchmandtC. (2000). Location-aware information delivery with commotion. Paper presented at the International Symposium on Handheld and Ubiquitous Computing, Bristol, UK.
12.
MatsuoY.OkazakiN.IzumiK.NakamuraY.NishimuraT.HasidaK. (2007). Inferring long-term user properties based on users' location history. Paper presented at the IJCAI 2007, Hyderabad, India.
13.
TangJ.MengL. (2006). Learning significant locations from GPS data with time window. Paper presented at the Geoinformatics, Reston, Virginia, USA.
14.
WilsonD. H.LongA. C.AtkesonC. (2005). A context-aware recognition survey for data collection using ubiquitous sensors in the home. Paper presented at the CHI 2005, Portland, Oregon, USA.
15.
WolfJ.GuenslerR.BachmannW. (2001). Elimination of the travel diary: An experiment to derive trip purpose from GPS travel data. Paper presented at the Transportation Research Board 80th Annual Meeting, Washington, DC.
16.
ZhangK.LiH.TorkkolaK.GardnerM. (2007). Adaptive learning of semantic locations and routes. Paper presented at the Autonomics, Rome, Italy.
17.
ZimmermannA.LorenA. (2003). Listen: Contextualized presentation for audio-augmented environments. Paper presented at the 11th Workshop on Adaptivity and User modelling in Interactive Systems, Karlsruhe, Germany.
