000192387 001__ 192387
000192387 005__ 20181001181855.0
000192387 02470 $$2ISI$$a000336519700005
000192387 0247_ $$2doi$$a10.1016/j.pmcj.2013.03.006
000192387 037__ $$aARTICLE
000192387 245__ $$aWhere and What: Using Smartphones to Predict Next Locations and Applications in Daily Life
000192387 269__ $$a2013
000192387 260__ $$c2013
000192387 336__ $$aJournal Articles
000192387 520__ $$aThis paper investigates the prediction of two aspects of human behavior us- ing smartphones as sensing devices. We present a framework for predicting where users will go and which app they will use in the next ten minutes by ex- ploiting the rich contextual information from smartphone sensors. Our first goal is to understand which smartphone sensor data types are important for the two prediction tasks. Secondly, we aim at extracting generic (i.e., user- independent) behavioral patterns and study how generic behavior models can improve the predictive performance of personalized models. Experimen- tal validation was conducted on the Lausanne Data Collection Campaign (LDCC) dataset, with longitudinal smartphone data collected over a period of 17 months from 71 users.
000192387 6531_ $$aSmartphone data
000192387 6531_ $$aHuman behavior
000192387 6531_ $$aMobility prediction
000192387 6531_ $$aApp usage prediction
000192387 6531_ $$aLausanne Data Collection Campaign
000192387 700__ $$aDo, Trinh-Minh-Tri
000192387 700__ $$0241066$$aGatica-Perez, Daniel$$g171600
000192387 773__ $$j12$$q79-91$$tPervasive and Mobile Computing
000192387 8564_ $$s452217$$uhttps://infoscience.epfl.ch/record/192387/files/Do_PMC_2013.pdf$$yn/a$$zn/a
000192387 909C0 $$0252189$$pLIDIAP$$xU10381
000192387 909CO $$ooai:infoscience.tind.io:192387$$pSTI$$particle$$qGLOBAL_SET
000192387 917Z8 $$x148230
000192387 937__ $$aEPFL-ARTICLE-192387
000192387 973__ $$aEPFL$$rNON-REVIEWED$$sPUBLISHED
000192387 970__ $$aDo_PMC_2013/LIDIAP
000192387 980__ $$aARTICLE