Trajectory Prediction Based on the Notion of Time and the Influence of Location of Historical Time Step

DOI

10.2991/cimns-16.2016.36How to use a DOI?

Keywords

trajectory prediction; markov chain; spatial-temporal data

Abstract

The development of wireless communication technology, sensor technology and so on, the spatial-temporal data record objects' movement that provide massive information about the activity regularity, due to the close relation between the mobile terminal and human. In this paper, we present a model of predicting the next location of an object that moves on the ground based on Markov chains that we coined as K time steps trajectory prediction algorithm (K-TSTP). We consider not only the spatial historical data but also consider the notion of time and the influence of location of historical time step in the prediction model. In order to evaluate the efficiency of our proposed prediction model, we use the data set that provided by Unicom. Experimental results show that our K-TSTP algorithm has increased the accuracy and reduced the execution time of prediction than the original Markov chain.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Fangxin Liu
AU  - Ming He
AU  - Yong Liu
AU  - Huan Zhou
AU  - Qiuli Chen
PY  - 2016/09
DA  - 2016/09
TI  - Trajectory Prediction Based on the Notion of Time and the Influence of Location of Historical Time Step
BT  - Proceedings of the 2016 International Conference on Communications, Information Management and Network Security
PB  - Atlantis Press
SP  - 142
EP  - 145
SN  - 2352-538X
UR  - https://doi.org/10.2991/cimns-16.2016.36
DO  - 10.2991/cimns-16.2016.36
ID  - Liu2016/09
ER  -