Radio-based Traffic Flow Detection and Vehicle Classification for Future Smart Cities.

Intelligent Transportation Systems (ITSs) providing vehicle-relatedstatistical data are one of the key components for future smart cities. In thiscontext, knowledge about the current traffic flow is used for travel timereduction and proactive jam avoidance by intelligent traffic controlmechanisms. In addition, the monitoring and classification of vehicles can beused in the field of smart parking systems. The required data is measured usingnetworks with a wide range of sensors. Nevertheless, in the context of smartcities no existing solution for traffic flow detection and vehicleclassification is able to guarantee high classification accuracy, lowdeployment and maintenance costs, low power consumption and aweather-independent operation while respecting privacy. In this paper, wepropose a radiobased approach for traffic flow detection and vehicleclassification using signal attenuation measurements and machine learningalgorithms. The results of comprehensive measurements in the field prove itshigh classification success rate of about 99%.