关键词: 调制识别, 边际谱, 复杂度, RBF神经网络, 分形原理

Abstract: On the basis of the marginal spectrum and complexity theory, a new feature extraction method is proposed to improve the accuracy of the digital modulation recognition under the low signal-to-noise ratio. Firstly, the Hilbert-Huang Transform is put forward to obtain the marginal spectrum of the samples. Secondly, the fractal dimensions and the Lempel-Ziv complexity of the samples after Hilbert-Huang Transform are calculated to extract the feature parameters. Finally, the identification problem is solved by using artificial neural network. The simulation results verify the performance of the proposed algorithm.

Key words: modulation recognition, marginal spectrum, complexity measure, RBF neural network, fractals theory