Antenna Classification Using Gaussian Mixture Models (GMM) and Machine Learning

Abstract

Radio frequency fingerprinting (RFF) is the concept arising from classification of wireless emitters due to their unique radio frequency features. RFF has been further extended to applications including both RF devices classification and wireless signal identification. In this paper, we adopt Gaussian Mixture Models (GMM) technique as feature extraction approach and firstly apply it to extract RFF of antennas. 9 classical antennas with 3 different load conditions (open, short, match) were studied in our experiment. Moreover, we also made a theoretical analysis about the reason scattered signal has the unique features. Specifically, we adopt the Random Noise Radar (RNR) technique to obtain reflected RF signals of antenna under test (AUT) and apply the GMM technique to fit RF signals and then extract the RFF of AUT. A support vector machine (SVM) is proposed to recognize the RFF at different signal-to-noise ratio (SNR) environment. Compared with the conventional feature extraction approaches, for example, from variance, skewness and kurtosis (VSK) values, our method demonstrates better performance on large datasets with classification accuracy above 88% using a SVM classifier. Moreover, the accuracy remains higher than 75% even when the Signal to Noise Ratio (SNR) is equal to 0dB, indicating that the proposed approach has the strong capability of noise immunity.