Algorithms for Automatic Modulation Recognition in Wireless Monitoring Applications

The paper proposes an automatic modulation recognition scheme based on instantaneous features of intercepted signals. The modulation classifier can discriminate modulations such as Amplitude Modulation (AM), Double Side Band (DSB), Single Side Band (SSB), Frequency Modulation (FM), M-ary Amplitude Shift Keying (M-ASK), M-ary Frequency Shift Keying (M-FSK), M-ary Phase Shift Keying (M-PSK) and M-ary Quadrature Amplitude Modulation (M-QAM) without any prior information. The scheme is with simple structure, computationally simpler, and suitable for real-time processing. And the recognition parameters are anti-noise, and insensitive to frequency offset, phase offset and timing error. To evaluate the performance of the scheme, several experiments with signals in Additive White Gaussian Noise (AWGN) channel were carried out in the MATLAB by varying the values of both the main modulation parameters and the signal-to-noise ratios (SNRs). The results show that the approach can achieve high recognition accuracy even at low SNR.