Automatic Modulation Classification of Digital Modulation Signals Based on Gaussian Mixture Model

In this paper, we propose an automatic modulation classification scheme for digitally modulated signals, such as MSK, GMSK, BPSK, QPSK, 8-PSK, 16-QAM, 32-QAM, and 64-QAM. As features which characterize the modulation type, higher order cyclic cumulants up to eighth order of the signal are used. For feature classification, a Gaussian mixture model based algorithm is used. Simulation results are demonstrated to evaluate the performance of the proposed scheme under AWGN channels. Keywordsautomatic modulation classification; Gaussian mixture model; cyclostationary; higher order cyclic cumulants.