2016, 38(3): 674-680.
doi: 10.11999/JEIT150747
Abstract:
To recognize the major modulation schemes which are applied to concurrent communication systems, a joint method based on the high-order cumulants and cyclic spectrum with intelligent decision algorithm (neural network) is proposed to recognize the modulation schemes for digital signals. Firstly, a new featured parameter is extracted from the four-order and six-order cumulants of the digital signals to identify the modulation schemes of {BPSK, 2ASK}, {QPSK}, {2FSK, 4FSK}, {MSK}, and {16QAM, 64QAM}, then {OFDM}, {16QAM, 64QAM}, {2ASK, BPSK}, and {2FSK, 4FSK} are classified by the other featured parameters of the joint high-order cumulants and cyclic spectrum algorithms. In order to facilitate the engineering implementation, the semi-physical simulation and mixed programming of LabVIEW and MATLAB are used to validate the proposed algorithms. Simulation results show that the algorithms can recognize modulations {OFDM, BPSK, QPSK, 2ASK, 2FSK, 4FSK, MSK, 16QAM, 64QAM} with small Signal-to-Noise Ratio (SNR). The average recognition rate is more than 94% with SNR greater or equal than 5 dB, which validates the effectiveness of the proposed algorithms.