Spatio-Tempo-Socio-Semantic-Aware Model For destination prediction in VANET

VANETs have attracted researchers' attention lately because of the need to promote the driving experience by extending the drivers' view through wireless data exchange. Mobility prediction enables appealing proactive experiences for a wide range of VANET location-aware services and applications. In this work, we present more than a destination prediction technique. We introduce a mechanism for transforming the vehicles into smart entities based on a four dimensional model for destination prediction. The model comprises all possible aspects affecting the human mobility including time, social network and locations preference. Moreover, it takes the lead in leveraging the semantic properties of both the points of interest and the social relations to affect the visiting activities of the drivers. The experimental results demonstrate that our model significantly outperforms the state-of-the-art approaches achieving an average accuracy of 90%. In addition, the presented approach lays the groundwork for a realistic mobility model capable of simulating the mobility activities of an input social network with great precision, independently of any input trace.