Skip to Main Content
Automatic modulation recognition is a topic of interest in many fields including signal surveillance, multi-user detection and radio frequency spectrum monitoring. In this paper, we present an algorithm for recognition of different types of continuous phase modulation signals that uses a combination of features extracted through cyclic spectral analysis and an ICA-SVM hybrid recognition system. Simulation results demonstrate the ability of the algorithm to correctly identify modulation types over a wide range of SNR scenarios. The effects of pulse shaping and partial response waveforms are also investigated.