Utilization of Markov Model and Non-Parametric Belief Propagation for Activity-Based Indoor Mobility Prediction in Wireless Networks

Abstract

A foremost objective in wireless networks is to facilitate the communication of mobile users and the widespread tracking and prediction of their mobility regardless of their point of attachment to the network. In indoor environments the effective users' motion prediction system and wireless localization technology play an important role in all aspects of people's daily lives, including e.g. living assistant, navigation, emergency detection, surveillance/tracking of target-of-interest, evacuation purposes, and many other location-based services. Prediction techniques that are currently used do not consider the motivation behind the movement of mobile nodes and incur huge overheads to manage and manipulate the information required to make predictions. In this paper we propose an activity-based continuous-time Markov model to define and predict the human movement patterns. Then we demonstrate the utility of Nonparametric Belief Propagation (NBP) technique in particle filtering, for both estimating the node locations and representing location uncertainties, and for prediction of the areas that would be visited and those that would not in the future. NBP method admits a wide variety of statistical models, and can represent multi-modal uncertainty. This prediction system may be used as an additional input into intelligent building automation systems.