A Machine Learning-based Approach for Vehicular Tracking in Low Power Wide Area Networks

This paper addresses the issue of monitoring and tracking people and vehicles within smart cities. The actors in this work jointly cooperate in sensing, sensible data processing, anonymized data delivery, and data processing, with the final goal of providing real-time mapping of vehicular and pedestrian concentration conditions. The classification of conditions can bring out critical situations that can be communicated in real-time to citizens. Tests were conducted in the city of Cagliari, Italy.