Generalized Dimension of Modulation Signals Using Morphological Covering Method

Automatic modulation recognition has become an important issue in various application areas such as civil and military domains. Feature extraction is a key step in modulation recognition tasks. In this work, we present a novel feature extraction scheme for modulation recognition by utilizing the generalized dimension based on the morphological covering method. Four typical modulation signals, mean the ASK, PSK, FSK and QAM signals, are simulated to verify the effectiveness of the presented method. Experimental results have revealed that the generalized dimension calculated by morphological covering can satisfactorily distinguish the four modulation types.