Modulation recognition of communication signal based on wavelet RBF neural network

Modulation recognition of communication signal is to confirm the modulation style of communication signal in the condition with much noise. Wavelet transformation has a good localization characteristic in time-frequency domain, while the neural network has characteristics of self-studying, self-adaptation, and high stabilization and can improve the autoimmunization and intelligence of recognition. We adopted the ideal of combination of wavelet and neural network in the paper, firstly, we used the wavelet to decompose the signal, and then abstracted the characteristic through the wavelet coefficient, lastly we adopted the RBF(Radial Basis Funtion) nerual network to recognize 4 kinds of common digital communication signal. The simulation results indicate that the presented method performs well.

[1]  Joohwan Chun,et al.  Classification of digital modulations using the LPC , 2000, Proceedings of the IEEE 2000 National Aerospace and Electronics Conference. NAECON 2000. Engineering Tomorrow (Cat. No.00CH37093).

[2]  R. Mammone,et al.  A new method of modulation classification for digitally modulated signals , 1992, MILCOM 92 Conference Record.

[3]  N. P. Ta.  A wavelet packet approach to radio signal modulation classification , 1994, Proceedings of ICCS '94.

[4]  K. C. Ho,et al.  Modulation identification by the wavelet transform , 1995, Proceedings of MILCOM '95.

[5]  S. S. Soliman,et al.  Automatic modulation recognition of digitally modulated signals , 1989, IEEE Military Communications Conference, 'Bridging the Gap. Interoperability, Survivability, Security'.

[6]  K. C. Ho,et al.  Modulation identification of digital signals by the wavelet transform , 2000 .

[7]  K. C. Ho,et al.  Identification of digital modulation types using the wavelet transform , 1999, MILCOM 1999. IEEE Military Communications. Conference Proceedings (Cat. No.99CH36341).