A hybrid Markov-based model for human mobility prediction

Abstract Human mobility behavior is far from random, and its indicators follow non-Gaussian distributions. Predicting human mobility has the potential to enhance location-based services, intelligent transportation systems, urban computing, and so forth. In this paper, we focus on improving the prediction accuracy of non-Gaussian mobility data by constructing a hybrid Markov-based model, which takes the non-Gaussian and spatio-temporal characteristics of real human mobility data into account. More specifically, we (1) estimate the order of the Markov chain predictor by adapting it to the length of frequent individual mobility patterns, instead of using a fixed order, (2) consider the time distribution of mobility patterns occurrences when calculating the transition probability for the next location, and (3) employ the prediction results of users with similar trajectories if the recent context has not been previously seen. We have conducted extensive experiments on real human trajectories collected during 21 days from 3474 individuals in an urban Long Term Evolution (LTE) network, and the results demonstrate that the proposed model for non-Gaussian mobility data can help predicting people’s future movements with more than 56% accuracy.

[1]  Yue Wang,et al.  Mobility Prediction in Cellular Network Using Hidden Markov Model , 2010, 2010 7th IEEE Consumer Communications and Networking Conference.

[2]  Yu Zheng,et al.  Trajectory Data Mining , 2015, ACM Trans. Intell. Syst. Technol..

[3]  Alicia Rodríguez Carrión.  Contributions to the understanding of human mobility and its impact on the improvement of lightweight mobility prediction algorithms , 2016 .

[4]  Hojung Cha,et al.  Evaluating mobility models for temporal prediction with high-granularity mobility data , 2012, 2012 IEEE International Conference on Pervasive Computing and Communications.

[5]  Carlos García-Rubio,et al.  Performance Evaluation of LZ-Based Location Prediction Algorithms in Cellular Networks , 2010, IEEE Communications Letters.

[6]  Zbigniew Smoreda,et al.  Unravelling daily human mobility motifs , 2013, Journal of The Royal Society Interface.

[7]  Xiaohui Yu,et al.  NLPMM: A Next Location Predictor with Markov Modeling , 2014, PAKDD.

[8]  Wang-Chien Lee,et al.  Mining geographic-temporal-semantic patterns in trajectories for location prediction , 2013, ACM Trans. Intell. Syst. Technol..

[9]  Razvan Stanica,et al.  Mobile Traffic Analysis: a Survey , 2015 .

[10]  Arne Leijon,et al.  Bayesian Estimation of Beta Mixture Models with Variational Inference , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Shuai Zhang,et al.  Residual life prediction based on dynamic weighted Markov model and particle filtering , 2018, J. Intell. Manuf..

[12]  Yuanyuan Qiao,et al.  Prediction of User Mobility Pattern on a Network Traffic Analysis Platform , 2015, MobiArch.

[13]  Brian D. Noble,et al.  BreadCrumbs: forecasting mobile connectivity , 2008, MobiCom '08.

[14]  Markus Flierl,et al.  Bayesian estimation of Dirichlet mixture model with variational inference , 2014, Pattern Recognit..

[15]  Anind K. Dey,et al.  Navigate like a cabbie: probabilistic reasoning from observed context-aware behavior , 2008, UbiComp.

[16]  Xiaohui Yu,et al.  Mining moving patterns for predicting next location , 2015, Inf. Syst..

[17]  Fang Dong,et al.  When and where next: individual mobility prediction , 2012, MobiGIS.

[18]  Yuanyuan Qiao,et al.  Spatial and temporal mobility analysis in LTE mobile network , 2015, 2015 IEEE Wireless Communications and Networking Conference (WCNC).

[19]  John G. Cleary,et al.  Unbounded length contexts for PPM , 1995, Proceedings DCC '95 Data Compression Conference.

[20]  Alberto Cortés-Martín,et al.  Study of LZ-Based Location Prediction and Its Application to Transportation Recommender Systems , 2012, Sensors.

[21]  Yuanyuan Qiao,et al.  User location prediction with energy efficiency model in the Long Term‐Evolution network , 2016, Int. J. Commun. Syst..

[22]  Jun Guo,et al.  Dirichlet mixture modeling to estimate an empirical lower bound for LSF quantization , 2014, Signal Process..

[23]  Douglas M. Blough,et al.  Mobility prediction using future knowledge , 2007, MSWiM '07.

[24]  Sung-Bae Cho,et al.  A HMM-Based Location Prediction Framework with Location Recognizer Combining k-Nearest Neighbor and Multiple Decision Trees , 2013, HAIS.

[25]  Nei Kato,et al.  Global and individual mobility pattern discovery based on hotspots , 2015, 2015 IEEE International Conference on Communications (ICC).

[26]  Dominique Barth,et al.  A hierarchical prediction model for two nodes-based IP mobile networks , 2009, MSWiM '09.

[27]  Sheetal Kalyani,et al.  A Modified PPM Algorithm for Online Sequence Prediction Using Short Data Records , 2015, IEEE Communications Letters.

[28]  Luis González Abril,et al.  Trip destination prediction based on past GPS log using a Hidden Markov Model , 2010, Expert Syst. Appl..

[29]  Leïla Kloul,et al.  A New Markov-Based Mobility Prediction Algorithm for Mobile Networks , 2010, EPEW.

[30]  J. Trinder,et al.  Smoothing Parameter Estimation for Markov Random Field Classification of non-Gaussian Distribution Image , 2014 .

[31]  Wen Zhou,et al.  Two Approaches for Statistical Prediction of Non-Gaussian Climate Extremes: A Case Study of Macao Hot Extremes during 1912-2012 , 2015 .

[32]  T. Ungerer,et al.  Next Location Prediction Within a Smart Office Building , 2005 .

[33]  Dominique Barth,et al.  Combining local and global profiles for mobility prediction in LTE femtocells , 2012, MSWiM '12.

[34]  M. Barthelemy,et al.  From mobile phone data to the spatial structure of cities , 2014, Scientific Reports.

[35]  Bruno Martins,et al.  Predicting future locations with hidden Markov models , 2012, UbiComp.

[36]  Chaoming Song,et al.  Modelling the scaling properties of human mobility , 2010, 1010.0436.

[37]  Marinka Zitnik,et al.  Gene network inference by fusing data from diverse distributions , 2015, Bioinform..

[38]  Vibhav Gogate,et al.  Modeling Transportation Routines using Hybrid Dynamic Mixed Networks , 2005, UAI.

[39]  Stefano Secci,et al.  Estimating human trajectories and hotspots through mobile phone data , 2014, Comput. Networks.

[40]  Brijesh Kumar Chaurasia,et al.  Gaussian Profile based Vehicular Mobility Modeling , 2011 .

[41]  Javad Akbari Torkestani,et al.  Mobility prediction in mobile wireless networks , 2012, J. Netw. Comput. Appl..

[42]  Ravi Jain,et al.  Evaluating Next-Cell Predictors with Extensive Wi-Fi Mobility Data , 2006, IEEE Transactions on Mobile Computing.

[43]  Albert-László Barabási,et al.  Understanding individual human mobility patterns , 2008, Nature.

[44]  T. Geisel,et al.  The scaling laws of human travel , 2006, Nature.

[45]  Thad Starner,et al.  Using GPS to learn significant locations and predict movement across multiple users , 2003, Personal and Ubiquitous Computing.

[46]  Nei Kato,et al.  A Mobility Analytical Framework for Big Mobile Data in Densely Populated Area , 2017, IEEE Transactions on Vehicular Technology.

[47]  Kari Laasonen,et al.  Clustering and Prediction of Mobile User Routes from Cellular Data , 2005, PKDD.

[48]  Shaojie Qiao,et al.  A Self-Adaptive Parameter Selection Trajectory Prediction Approach via Hidden Markov Models , 2015, IEEE Transactions on Intelligent Transportation Systems.

[49]  Sung-Bae Cho,et al.  Exploiting machine learning techniques for location recognition and prediction with smartphone logs , 2016, Neurocomputing.

[50]  Arne Leijon,et al.  Vector quantization of LSF parameters with a mixture of dirichlet distributions , 2013, IEEE Transactions on Audio, Speech, and Language Processing.

[51]  Stathes Hadjiefthymiades,et al.  Efficient Location Prediction in Mobile Cellular Networks , 2012, Int. J. Wirel. Inf. Networks.

[52]  Zhifeng Zhao,et al.  Human Mobility Patterns in Cellular Networks , 2013, IEEE Communications Letters.

[53]  Ravi Jain,et al.  Predictability of WLAN Mobility and Its Effects on Bandwidth Provisioning , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[54]  Daqiang Zhang,et al.  MPaaS: Mobility prediction as a service in telecom cloud , 2013, Information Systems Frontiers.

[55]  Mark F. J. Steel,et al.  Non-Gaussian and nonparametric models for continuous spatial data , 2010 .

[56]  Daniel Gatica-Perez,et al.  A probabilistic kernel method for human mobility prediction with smartphones , 2015, Pervasive Mob. Comput..

[57]  Jun Pang,et al.  Constructing and Comparing User Mobility Profiles , 2014, TWEB.