Unsupervised Drones Swarm Characterization Using RF Signals Analysis and Machine Learning Methods

Autonomous unmanned aerial vehicles (UAVs) have attracted increasing academic and industrial attention during the last decade. Using drones have broad benefits in diverse areas, such as civil and military applications, aerial photography and videography, mapping and surveying, agriculture, and disaster management. However, the recent development and innovation in the field of drone (UAV) technology have led to malicious usage of the technology, including the penetration of secure areas (such as airports) and serving terrorist attacks. Autonomous weapon systems might use drone swarms to perform more complex military tasks. Utilizing a large number of drones, simultaneously increases the risk and the reliability of the mission in terms of redundancy, survivability, scalability, and the quality of autonomous performance in a complex environment. This research suggests a new approach for drone swarm characterization and detection using RF signals analysis and various machine learning methods. While most of the existing drone detection and classification methods are typically related to a single drone classification, using supervised approaches, this research work proposes an unsupervised approach for drone swarm characterization. The proposed method utilizes the different radio frequency (RF) signatures of the drone's transmitters. Various kinds of frequency transform, such as the continuous, discrete, and wavelet scattering transform, have been applied to extract RF features from the radio frequency fingerprint, which have then been used as input for the unsupervised classifier. To reduce the input data dimension, we suggest using unsupervised approaches such as Principal component analysis (PCA), independent component analysis (ICA), uniform manifold approximation and projection (UMAP), and the t-distributed symmetric neighbor embedding (t-SNE) algorithms. The proposed clustering approach is based on common unsupervised methods, including K-means, mean shift, and X-means algorithms. The proposed approach has been evaluated using self-built and common drone swarm datasets. The results demonstrate a classification accuracy of about 95% under additive Gaussian white noise with different levels of SNR.