Classification of Digital Modulations Mainly Used in Mobile Radio Networks by means of Spectrogram Analysis

In this paper a new method of modulation classification is proposed. For the analysis, modulation signals and their spectrograms were obtained in the Matlab program. The classification method is based on spectrogram image recognition and it can discriminate between various digital signal modulations, such as FSK, BPSK, MSK, QPSK and QAM. The new method was tested using modulated signals corrupted by Gaussian noise, and it is well usable with signal-to-noise ratios as low as 10 dB.