Individual Radio Frequency Interference Identification on VHF Radar Based on SVM Classifier

To realize individual radio frequency interference identification on the very high frequency (VHF) radar signals, a nonlinear characteristic, namely, the chaotic characteristics of the radio frequency interference transient signal is studied and proved to be the fingerprint features of the individual radio frequency interference on VHF radar signals. Furthermore, the support vector machine classifier based on particle swarm optimization(PSO) is designed. Finally, The numerical and real data have proved that this method is not only effective but also still has a high recognition rate in the case of small samples to adapt to the battlefield environment, and has broad application prospects.

[1]  Ralph D. Hippenstiel,et al.  Wavelet Based Transmitter Identification , 1996, Fourth International Symposium on Signal Processing and Its Applications.

[2]  J. Platt.  Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector Machines , 1998 .

[3]  O. Ureten,et al.  Generalised dimension characterisation of radio transmitter turn-on transients , 2000 .

[4]  A. Wolf,et al.  Determining Lyapunov exponents from a time series , 1985 .

[5]  Les E. Atlas,et al.  Optimizing time-frequency kernels for classification , 2001, IEEE Trans. Signal Process..

[6]  Russell C. Eberhart,et al.  A new optimizer using particle swarm theory , 1995, MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science.

[7]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[8]  N. Huang,et al.  A study of the characteristics of white noise using the empirical mode decomposition method , 2004, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[9]  S. Sathiya Keerthi,et al.  Improvements to Platt's SMO Algorithm for SVM Classifier Design , 2001, Neural Computation.

[10]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[11]  E P Souza Neto,et al.  Assessment of Cardiovascular Autonomic Control by the Empirical Mode Decomposition , 2004, Methods of Information in Medicine.

[12]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[13]  G. P. King,et al.  Extracting qualitative dynamics from experimental data , 1986 .

[14]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[15]  Yuan Yan Tang,et al.  Extraction of fractal feature for pattern recognition , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[16]  Les E. Atlas,et al.  Class-dependent, discrete time-frequency distributions via operator theory , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.