TY - JOUR
T1 - Big Data Driven Hidden Markov Model Based Individual Mobility Prediction at Points of Interest
AU - Lv, Qiujian
AU - Qiao, Yuanyuan
AU - Ansari, Nirwan
AU - Liu, Jun
AU - Yang, Jie
N1 - Funding Information:
Manuscript received March 31, 2016; revised July 27, 2016; accepted September 11, 2016. Date of publication September 20, 2016; date of current version June 16, 2017. This work was supported in part by the National Natural Science Foundation of China under Grant 61671078 and Grant 61601042, the Fundamental Research Funds for the Central Universities (2015RC11), the Director Foundation Project (2015BKL-NSAC-ZJ-01), 111 Project of China (B08004), and the EU FP7 IRSES MobileCloud Project under Grant 612212. The review of this paper was coordinated by Dr. Y. Song.
Publisher Copyright:
© 1967-2012 IEEE.
PY - 2017/6
Y1 - 2017/6
N2 - With the emergence of smartphones and location-based services, user mobility prediction has become a critical enabler for a wide range of applications, like location-based advertising, early warning systems, and citywide traffic planning. A number of techniques have been proposed to either conduct spatiooral mobility prediction or forecast the next-place. However, both produce diverse prediction performance for different users and display poor performance for some users. This paper focuses on investigating the effect of living habits on the models of spatiooral prediction and next-place prediction, and selects one from these two models for an individual to achieve effective mobility prediction at users' points of interest. Based on the hidden Markov model (HMM), a spatiooral predictor and a next-place predictor are proposed. Living habits are analyzed in terms of entropy, upon which users are clustered into distinct groups. With large-scale factual mobile data captured from a big city, we compare the proposed HMM-based predictors with existing state-of-the-art predictors and apply them to different user groups. The results demonstrate the robust performance of the two proposed mobility predictors, which outperform the state of the art for various user groups.
AB - With the emergence of smartphones and location-based services, user mobility prediction has become a critical enabler for a wide range of applications, like location-based advertising, early warning systems, and citywide traffic planning. A number of techniques have been proposed to either conduct spatiooral mobility prediction or forecast the next-place. However, both produce diverse prediction performance for different users and display poor performance for some users. This paper focuses on investigating the effect of living habits on the models of spatiooral prediction and next-place prediction, and selects one from these two models for an individual to achieve effective mobility prediction at users' points of interest. Based on the hidden Markov model (HMM), a spatiooral predictor and a next-place predictor are proposed. Living habits are analyzed in terms of entropy, upon which users are clustered into distinct groups. With large-scale factual mobile data captured from a big city, we compare the proposed HMM-based predictors with existing state-of-the-art predictors and apply them to different user groups. The results demonstrate the robust performance of the two proposed mobility predictors, which outperform the state of the art for various user groups.
KW - Big data
KW - cellular data network
KW - hidden Markov model (HMM)
KW - next-place prediction
KW - spatiooral mobility prediction
UR - http://www.scopus.com/inward/record.url?scp=85028756317&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85028756317&partnerID=8YFLogxK
U2 - 10.1109/TVT.2016.2611654
DO - 10.1109/TVT.2016.2611654
M3 - Article
AN - SCOPUS:85028756317
SN - 0018-9545
VL - 66
SP - 5204
EP - 5216
JO - IEEE Transactions on Vehicular Technology
JF - IEEE Transactions on Vehicular Technology
IS - 6
M1 - 7572081
ER -