000202568 001__ 202568
000202568 005__ 20190317000032.0
000202568 0247_ $$2doi$$a10.1016/j.pmcj.2014.09.001
000202568 02470 $$2ISI$$a000355199300002
000202568 037__ $$aARTICLE
000202568 245__ $$aA Probabilistic Kernel Method for Human Mobility Prediction with Smartphones
000202568 269__ $$a2015
000202568 260__ $$c2015
000202568 336__ $$aJournal Articles
000202568 520__ $$aHuman mobility prediction is an important problem which has a large num- ber of applications, especially in context-aware services. This paper presents a study on location prediction using smartphone data, in which we address mod- eling and application aspects. Building personalized location prediction models from smartphone data remains a technical challenge due to data sparsity, which comes from the complexity of human behavior and the typically limited amount of data available for individual users. To address this problem, we propose an approach based on kernel density estimation, a popular smoothing technique for sparse data. Our approach contributes to existing work in two ways. First, our proposed model can estimate the probability that a user will be at a given location at a specific time in the future, by using both spatial and temporal information via multiple kernel functions. Second, we also show how our prob- abilistic framework extends to a more practical task of location prediction for a time window in the future. Our approach is validated on an everyday life location datasets consisting of 133 smartphone users. Our method reaches an accuracy of 84% for the next hour, and an accuracy of 77% for the next three hours.
000202568 6531_ $$ahuman mobility
000202568 6531_ $$apersonalized service
000202568 6531_ $$aprediction
000202568 6531_ $$aSmartphones
000202568 700__ $$aDo, Trinh-Minh-Tri
000202568 700__ $$aDousse, O.
000202568 700__ $$aMiettinen, Markus
000202568 700__ $$g171600$$aGatica-Perez, Daniel$$0241066
000202568 773__ $$j20$$tPervasive and Mobile Computing$$q13-28
000202568 8564_ $$uhttps://infoscience.epfl.ch/record/202568/files/Do_PMC_2014.pdf$$zn/a$$s543808$$yn/a
000202568 909C0 $$xU10381$$0252189$$pLIDIAP
000202568 909CO $$ooai:infoscience.tind.io:202568$$qGLOBAL_SET$$pSTI$$particle
000202568 917Z8 $$x148230
000202568 937__ $$aEPFL-ARTICLE-202568
000202568 970__ $$aDo_PMC_2014/LIDIAP
000202568 973__ $$rNON-REVIEWED$$sPUBLISHED$$aEPFL
000202568 980__ $$aARTICLE