Multi-signals Modulation Recognition Based on Cyclic Spectrum and Sparse Representation

For the modulation recognition problem of several time-frequency overlapping modulation signals,a new method that can identify the signals mixed signal types without separation is proposed. For different cyclic spectrum of different modulation signals,the features can be extracted by using sparse representation,and finally according to the extracted feature,support vector machine is used to recognition and classification. Theoretical analysis and experimental simulations obtain that this method has a certain robustness of noise,it still has a good recognition performance at low SNR. When the SNR is-4 d B,the correct recognition rate of single and mixed signals can respectively reach 93. 5% and 90. 67%.