TY - JOUR
T1 - A Survey for Mobility Big Data Analytics for Geolocation Prediction
AU - Xu, Guangxia
AU - Gao, Shiyi
AU - Daneshmand, Mahmoud
AU - Wang, Chonggang
AU - Liu, Yanbing
N1 - Publisher Copyright:
© 2002-2012 IEEE.
PY - 2017/2
Y1 - 2017/2
N2 - Geolocation prediction (GP) can be applied to geolocation-based services (GBS), which could provide future services for application users and expand its field of application. Typical geolocation prediction schemes include Markov- based and Bayesian network-based methods. Emerging mobility big data (MBD) poses new challenges and opportunities for geolocation prediction. Because of the diversity of geolocation data, geolocation prediction can be divided into two primary parts: the mining popular geolocation region (MPGR), which is the first step in preprocessing geolocation data when building a geolocation prediction model (GPM); and mining personal trajectory (MPT), which is the second step in building a geolocation prediction model. This article aims to survey existing solutions for geolocation prediction in the era of mobility big data. It first introduces the concepts, classifications, and characteristics of geolocation prediction. Then it describes the basic principles and characteristics of mining popular geolocation regions and mining personal trajectory. This article also discusses challenges, opportunities, and future directions of mobility data analytics for geolocation prediction.
AB - Geolocation prediction (GP) can be applied to geolocation-based services (GBS), which could provide future services for application users and expand its field of application. Typical geolocation prediction schemes include Markov- based and Bayesian network-based methods. Emerging mobility big data (MBD) poses new challenges and opportunities for geolocation prediction. Because of the diversity of geolocation data, geolocation prediction can be divided into two primary parts: the mining popular geolocation region (MPGR), which is the first step in preprocessing geolocation data when building a geolocation prediction model (GPM); and mining personal trajectory (MPT), which is the second step in building a geolocation prediction model. This article aims to survey existing solutions for geolocation prediction in the era of mobility big data. It first introduces the concepts, classifications, and characteristics of geolocation prediction. Then it describes the basic principles and characteristics of mining popular geolocation regions and mining personal trajectory. This article also discusses challenges, opportunities, and future directions of mobility data analytics for geolocation prediction.
UR - http://www.scopus.com/inward/record.url?scp=84994316408&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84994316408&partnerID=8YFLogxK
U2 - 10.1109/MWC.2016.1500131WC
DO - 10.1109/MWC.2016.1500131WC
M3 - Article
AN - SCOPUS:84994316408
SN - 1536-1284
VL - 24
SP - 111
EP - 119
JO - IEEE Wireless Communications
JF - IEEE Wireless Communications
IS - 1
M1 - 7731599
ER -