Cumulant based Kolmogorov-Smirnov spectrum sensing

In this paper, we propose a Cumulant Kolmogorov-Smirnov (KS) test for spectrum sensing in Cognitive Radio networks. The KS test is a kind of goodness of fit test that quantifies a distance between the empirical distribution functions of the received signals and the channel noise samples. Due to using 4^th order Cumulant statistics, the proposed KS detector has some advantages over previous detectors. We exert KS test to the estimated Cumulant vector and perform detection problem. The proposed method is nonparametric and needs only a short sequence of noise samples. In addition, it is not sensitive to noise uncertainty. Superiority of the proposed KS-based method is shown by comparing it with a popular KS method and the classical Energy Detector.