A New Modulation Recognition Method Based on Wavelet Transform and High-order Cumulants

Abstract

Abstract In order to improve the recognition performance of digital modulated signals under low signal-to-noise ratio, this paper proposes a new method that combines high-order cumulants and wavelet transform to extract transient features, and the recognition of six kinds of modulation signals is realized through the neural network classifier. Simulation results show that the proposed algorithm can achieve good performance under low signal-to-noise ratio. In addition, only three key features are selected in this method, which greatly reduces the complexity of the algorithm. Furthermore, the effects of sample rate, carrier frequency and symbol rate on recognition performance are analyzed and simulated for the sake of better recognition performance.