Distributed asynchronous modulation classification based on hybrid maximum likelihood approach

In this paper, we consider the problem of automatic modulation classification (AMC) with multiple sensors. A distributed hybrid maximum likelihood (HML) based algorithm in the presence of unknown time offset, phase offset and channel gain is presented. The proposed distributed algorithm that employs the generalized expectation maximization (GEM) algorithm is robust to initialization of unknown parameters, computationally efficient and require much less communication overhead compared to performing GEM in a centralized setting. Simulation and experimental results depict the efficacy of the proposed algorithm.