Automatic Modulation Recognition for MFSK Using Modified Covariance Method

Abstract

This paper presents modulation classification method capable of classifyingMFSK digital signals without a priori information using modified covariancemethod. This method using for calculation features for FSK modulationshould have a good properties of sensitive with FSK modulation index andinsensitive with signal to noise ratio SNR variation. The numericalsimulations and investigation of the performance by the support vectorsmachine one against all (SVM-OAA) as a classifier for classifying 6 digitallymodulated signals which gives probability of correction classification up to85.85 at SNR=-15dB.