摘要：Modulation identification for communication signals has important applications both in military and civilian areas. Aimed at the non-stationary modulated signal of which signal to noise ratio (SNR) changes large, a novel method for recognition of modulation signals by wavelet transform and neural network theory is introduced. In this algorithm, instantaneous feature parameters of received signals are extracted using wavelet transform. Then, make singular value decomposition to the matrix which is composed of instantaneous parameters to get singular values. Error back propagation neural network (BPNN) with supervised training is to be made the classifier. The singular values obtained are used as feature vector and inputted to the classifier. So the automatic modulation recognition of signal is realized. The identification in category for FSK and PSK are simulated respectively, and the simulation results prove the approach proposed in this paper is efficient.
关键词：recognition; feature vector extraction and matching; wavelet transform; singular value decomposition (SVD); error back propagation neural network (BPNN)
