Identification of Wi-Fi-enabled drones via software-defined radio (SDR) and artificial intelligence (AI)

Abstract

This thesis presents a method for detecting Wi-Fi-controlled drones using software-defined radio (SDR) technology combined with artificial intelligence (AI). Radio frequency (RF) signals in the 2.4 GHz band were captured and analyzed to distinguish drone transmissions from conventional wireless activity. A rule-based bandwidth analysis was first implemented, followed by a convolutional neural network (CNN) classifier trained on power spectral density (PSD) features. The system successfully identified drone signals in real time under test conditions, demonstrating that SDR combined with AI provides a cost-effective and extensible framework for RF-based drone detection.