PROJECT TITLE :

New Automatic Modulation Classifier Using Cyclic-Spectrum Graphs With Optimal Training Features - 2018

ABSTRACT:

A new feature-extraction paradigm for graph-based automatic modulation classification is proposed in this letter. Within the proposed new framework, the modulation features are optimally created using the Kullback-Leibler divergence of the dominant entries within the adjacency matrices related to the graph presentation of the cyclic spectra. Then, the Hamming distance is invoked to live the discrepancies between the features derived from the coaching and check knowledge to determine the modulation sort. The proposed algorithm, that can select the most distinguishable features, results in the promising solution to automatic modulation classification (AMC). Compared with the prevailing AMC approach based mostly on cyclic spectra, Monte Carlo simulation results demonstrate that the proposed AMC method using the new feature-extraction scheme is abundant more effective.