Robust and Reliable Modulation Classification for MIMO Systems

This paper develops a feature-based Automatic Modulation Classification (AMC) algorithm for spatially multiplexed Multiple-Input Multiple-Output (MIMO) systems. The proposed algorithm employs two Higher Order Cumulants (HOCs) of the estimated transmit signal streams as discriminating features, and a multiclass Support VectorMachine (SVM) as a classification system. A multi-classifier classification system is introduced to improve the robustness of the decision made by the classifier at each estimated transmit signal stream. Furthermore, an optimal decision fusion scheme using aMaximum-Likelihood (ML) criterion is also introduced to improve the accuracy and reliability of the final classification decision made in the fusion center. The proposed algorithm shows good performance under different operating conditions, over an acceptable range of SNR, without any prior information about the channel state