A Hybrid ICA-SVM Approach to Continuous Phase Modulation Recognition

Automatic modulation recognition is a topic of interest in many fields including signal surveillance, multi-user detection and radio frequency spectrum monitoring. In this paper, we present an algorithm for recognition of different types of continuous phase modulation signals that uses a combination of features extracted through cyclic spectral analysis and an ICA-SVM hybrid recognition system. Simulation results demonstrate the ability of the algorithm to correctly identify modulation types over a wide range of SNR scenarios. The effects of pulse shaping and partial response waveforms are also investigated.

[1]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[2]  Balu Santhanam,et al.  A Feature Weighted Hybrid ICA-SVM Approach to Automatic Modulation Recognition , 2009, 2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop.

[3]  Yuan Qi,et al.  Hybrid independent component analysis and support vector machine learning scheme for face detection , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[4]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[5]  William A. Gardner,et al.  Estimation of cyclic polyspectra , 1991, [1991] Conference Record of the Twenty-Fifth Asilomar Conference on Signals, Systems & Computers.

[6]  Balu Santhanam,et al.  A general approach towards blind multiuser detection using higher order statistics , 2006, IEEE Wireless Communications and Networking Conference, 2006. WCNC 2006..

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

[8]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[9]  W. A. Gardner,et al.  Performance of Optimum and Adaptive Frequency-Shift Filters for Cochannel Interference and Fading , 1990, 1990 Conference Record Twenty-Fourth Asilomar Conference on Signals, Systems and Computers, 1990..

[10]  Liang Hong,et al.  Classification of BPSK and QPSK signals in fading environment using the ICA technique , 2005, Proceedings of the Thirty-Seventh Southeastern Symposium on System Theory, 2005. SSST '05..

[11]  Asoke K. Nandi,et al.  Automatic digital modulation recognition using spectral and statistical features with multi-layer perceptrons , 2001, Proceedings of the Sixth International Symposium on Signal Processing and its Applications (Cat.No.01EX467).

[12]  T. Aulin,et al.  Continuous Phase Modulation - Part I: Full Response Signaling , 1981, IEEE Transactions on Communications.

[13]  William A. Gardner.  Two alternative philosophies for estimation of the parameters of time-series , 1991, IEEE Trans. Inf. Theory.

[14]  F. Liedtke.  Adaptive procedure for automatic modulation recognition , 2004 .

[15]  D. Zhang,et al.  Supergaussian data denoising by semi-ICA estimation , 2005, Proceedings of the Thirty-Seventh Southeastern Symposium on System Theory, 2005. SSST '05..

[16]  D.Z. Vucic,et al.  Cyclic spectral analysis of phase-incoherent FSK signal by matrix-based stochastic method , 2001, 5th International Conference on Telecommunications in Modern Satellite, Cable and Broadcasting Service. TELSIKS 2001. Proceedings of Papers (Cat. No.01EX517).