Prediction Using Markov for Determining Location of Human Mobility

Human mobility in urban area related to how people moved from a city to another city, whether by walking or using vehicles to support their mobility. By processing data of human mobility, we can determine prediction of the next pattern of human mobility. Some methods for human mobility prediction have been proposed. One of them is predication using Markov. In this research, we conducted implementation of Markov algorithm to predict location of human mobility based on input data form individual mobility dataset (GeoLife) from GPS. This research carried out through five stages of research and conducted between December 2017 until June 2018. The conclusions drawn from this study are the values for parameters such as HMM n_components = 5, covariance_type = 'spherical', and decoder algorithm = 'viterbi' which produces a curation of 0.769 and RMSE 1,641 can be said to be hmm good enough in modeling data.

[1]  L. Huang,et al.  Improved markov predictor in wireless networks , 2011, IET Commun..

[2]  Xing Xie,et al.  GeoLife2.0: A Location-Based Social Networking Service , 2009, 2009 Tenth International Conference on Mobile Data Management: Systems, Services and Middleware.

[3]  Wei-Ying Ma,et al.  Understanding mobility based on GPS data , 2008, UbiComp.

[4]  M.A. Teixeira,et al.  Fuzzy multi-hidden Markov predictor in electric load forecasting , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[5]  Achmad Nizar Hidayanto,et al.  Apdati: E-Fishing Logbook for integrated tuna fishing data management , 2015 .

[6]  Siyuan Liu,et al.  Urban human mobility data mining: An overview , 2016, 2016 IEEE International Conference on Big Data (Big Data).

[7]  Xing Xie,et al.  Discovering regions of different functions in a city using human mobility and POIs , 2012, KDD.

[8]  Xing Xie,et al.  Mining interesting locations and travel sequences from GPS trajectories , 2009, WWW '09.

[9]  Davy Janssens,et al.  Detecting urban road network accessibility problems using taxi GPS data , 2016 .

[10]  E. Ravenstein.  The Laws of Migration , 1885, Encyclopedia of Gerontology and Population Aging.

[11]  Reza Malekian,et al.  Vehicle trajectory prediction based on Hidden Markov Model , 2016, KSII Trans. Internet Inf. Syst..

[12]  Brett Browning,et al.  Learning to Predict Driver Route and Destination Intent , 2006, 2006 IEEE Intelligent Transportation Systems Conference.

[13]  Dino Pedreschi,et al.  Trajectory pattern mining , 2007, KDD '07.

[14]  Iti Saha Misra,et al.  A Fast Hardware Based Hidden Markov Model Predictor for Cognitive Radio , 2016, 2016 IEEE 6th International Conference on Advanced Computing (IACC).

[15]  Daqing Zhang,et al.  Measuring social functions of city regions from large-scale taxi behaviors , 2011, 2011 IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops).

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

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

[18]  Guannan Liu,et al.  A cost-effective recommender system for taxi drivers , 2014, KDD.

[19]  Xing Xie,et al.  Urban computing with taxicabs , 2011, UbiComp '11.