An Application of Markov Jump Process Model for Activity-Based Indoor Mobility Prediction in Wireless Networks

One of the most important objectives of a wireless network is to facilitate a prediction of users 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 peoples daily lives. In this paper we propose an activity-based continuous-time Markov model to define and predict the human movement patterns. This model is a simple extension of an Activity based Mobility Prediction algorithm using Markov modeling (AMPuMM) technique. Both models are experimentally evaluated in realistic small university campus scenario. The obtained results show us the high efficiency of the jump methodology in the prediction of the students activities in the indoor campus environment.