Location Recommendation on a Street Random Waypoint Mobility Model Based on Predictive Model

Mobile Ad-Hoc Network (MANET) is a collection of mobile nodes which form a temporary network through wireless devices – without requiring any existing infrastructure. In the real world, user’s behaviour is depended on many major factors such as weather, situation, location, date and time. While mobile nodes can move with diverse patterns, it is difficult to accurately predict the events henceforward. In this paper, we propose an intelligence location-based recommendation system to predict a new route destination prediction method based on the movement history. On the whole, the following steps outline the methodology of our studies: First, we collect the mobile user’s movement history. We begin by scrutinizing the characteristics of movement patterns all the way through mobility trace files obtained from GPS. Second, we demonstrate how prediction can be made using the mobility model parameters to investigate the influence of other parameter variations using Bayes' theorem. Third, we propose a recommendation system for adjusting the weight function adaptively. Finally, through a series of experiments, our proposed method aims to deliver performance in terms of accuracy and applicability under various system conditions.