Abnormal behavior detection of jamming signal in the spectrum using a combination of compressive sampling and intelligent bivariate k-means clustering technique in wideband cognitive radio systems

This paper presents a new method of detection based on the combination of compressed sampling (CS) and intelligent bivariate k-means clustering technique to detect the presence of jamming attack signal in the spectrum based on the the two proposed hypotheses H0 (absence of jamming) and H1 (presence of jamming). Using an Analog-to-Information Converter (AIC) via Random Demodulator (RD) in each radio receiver to realize compressive sampling. The compressed measurements obtained after applying CS for each radio receiver are collected in observation matrix of dimesion Y(M × N1), considered as an input of intelligent k-means clustering intelligent detector in the level of Fusion Center (FC) via centralized cooperation. The results obtained show that the original method performs good in addition to its low consumption energy and computation complexity.