Systems and methods for modulation classification of baseband signals using multiple data representations of signal samples

Abstract

Systems and methods for classifying radio frequency signal modulations include receiving, at a consolidated neural network, a complex quadrature vector of interest representative of a baseband signal derived from a radio frequency signal, generating multiple data representations of the vector of interest, providing each data representation to one of multiple parallel neural networks in the consolidated neural network, and receiving, from the consolidated neural network, a classification result for the baseband signal. The consolidated neural network may be trained to classify baseband signals with respect to known modulation types by receiving complex quadrature training vectors, each including samples of a baseband signal derived from a radio frequency signal of known modulation type, comparing a classification result for the training vector to the known modulation type to determine modulation classification performance, and modifying a configuration parameter of the consolidated neural network dependent on the determined modulation classification performance.