Automatic Modulation Recognition of MPSK Signals at Low SNR Situation

摘要

Automatic modulation identification plays an important role in intelligent communication. An improved approach, based on higher-order cumulants and support vector machine (SVM), is proposed for the classification of M-ary Phase Shift Keying (MPSK) signals at low signal-to-noise ratio (SINK) situation, and wavelet transform (WT) is applied to suppress noise via a new thresholding function. It is shown that the proposed algorithm has better performance than the existing approaches. Theoretical arguments are verified via extensive simulations. Simulation results indicate that the correct classification probability (Pcc) with proposed algorithm has improved about 5dB compared with the existing method.