Automatic modulation classification using modulation fingerprint extraction

An automatic method for classifying frequency shift keying (FSK), minimum (MSK), phase (PSK), quadrature amplitude modulation (QAM), and orthogonal division multiplexing (OFDM) is proposed by simultaneously using normality test, spectral analysis, geometrical characteristics of in-phase-quadrature (I-Q) constellation diagram. Since the extracted features are unique each modulation, they can be considered as a fingerprint modulation. We show that algorithm outperforms previously published methods in terms signal-to-noise ratio (SNR) success rate. For example, rate 64-QAM at SNR=11 dB 99%. Another advantage its wide SNR range; such probability classification 16-QAM SNR=3 almost 1. The also provides database I-Q By comparing correlating data provided with estimated diagram received signal, processing gain 4 obtained. Whatever mentioned about preference low complexity, SNR, range set, enhanced recognition higher-order modulations.