Drones Detection and Classification Based on RF Signal Pre-Processing Combing with Convolution Neural Network

In recent years, the development of science and technology has led to the increasing popularity of small unmanned aerial vehicles (UAVs) such as drones. With the convenience of use and the decreasing cost, the demand for using drones in civilian applications, from personal purposes such as filming and aerial photography to economic purposes such as transportation, will continue to increase. However, this will allow anyone using drones to access geographical areas that were previously inaccessible before the existence of drones. This will certainly cause many difficulties for the monitoring and management of restricted areas. In this study, we propose a solution for the detection and classification of drones based on RF signal preprocessing combined with a convolution neural network. The results of the proposed model verified on the real dataset achieved drones detection rate of 99% and drones classification rate of 84%.