A novel approach for automatic classification of digitally modulated signals in HF communications

In this paper, we propose a novel algorithm for automatic modulation classification of single carrier digital modulations widely used in High Frequency (HF) band that serves both military and civilian applications. Specifically, the proposed algorithm addresses the classification of 2FSK, 4FSK, 8FSK, 2PSK, 4PSK, 8PSK, 16QAM, 32QAM, 64QAM, and OQPSK using two features: Dissimilarity in constellation diagram for classification of PSK/QAM signals and spectral peaks for classification of FSK signals with the use of both Decision Tree (DT) and Support Vector Machine (SVM) classifiers. The robustness of proposed algorithm is tested against noise power and changes in noise model. Additive White Gaussian Noise (AWGN) and Bi-kappa noise models are considered in this work, as both exist in HF band.