Automatic Digital Modulation Recognition Using Support Vector Machines and Genetic Algorithm

A new method, based on support vector machines (SVMs) and genetic algorithm (GA), is proposed for automatic Intra-Pulse modulation recognition (AIMR). In particular, the best feature subset from the combined pulse descriptor word (PDW) feature set and time-frequency feature set is optimized using genetic algorithm. Compared to the conventional decision-theoretic method, the method proposed avoids the frequency ambiguity caused by signal noise. Simulation results show that this method is more robust and effective than other existing approaches, particularly at a low signal noise ratio (SNR).

[1]  Ali Abdi,et al.  Survey of automatic modulation classification techniques: classical approaches and new trends , 2007, IET Commun..

[2]  Elsayed Elsayed Azzouz,et al.  Algorithms for automatic modulation recognition of communication signals , 1998, IEEE Trans. Commun..

[3]  Brian M. Sadler,et al.  Hierarchical digital modulation classification using cumulants , 2000, IEEE Trans. Commun..

[4]  V. Koivunen,et al.  Automatic Radar Waveform Recognition , 2007, IEEE Journal of Selected Topics in Signal Processing.

[5]  Alon Orlitsky,et al.  On Nearest-Neighbor Error-Correcting Output Codes with Application to All-Pairs Multiclass Support Vector Machines , 2003, J. Mach. Learn. Res..

[6]  Monique P. Fargues,et al.  Feature extraction of intra-pulse modulated signals using time-frequency analysis , 2000, MILCOM 2000 Proceedings. 21st Century Military Communications. Architectures and Technologies for Information Superiority (Cat. No.00CH37155).

[7]  Elsayed Elsayed Azzouz,et al.  Modulation recognition using artificial neural networks , 1997, Signal Process..

[8]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.