A Faster Maximum-Likelihood Modulation Classification in Flat Fading Non-Gaussian Channels

Abstract

In this letter, we use squared iterative method with parameter checking to accelerate the convergence rate of expectation/conditional maximization (ECM) algorithm when estimating the channel parameters blindly in flat fading non-Gaussian channels, and further, we proposed automatic modulation classification (AMC) in flat fading non-Gaussian channels based on the proposed maximum likelihood estimator. The numerical results show that the proposed method can accelerate the convergence rate of ECM algorithm, and AMC based on the proposed method is faster than that based on ECM, while the accuracy of the former shows nearly no loss compared with that of the latter.