Automatic Classification of LFM Signals for Radar Emitter Recognition Using Wavelet Decomposition and LVQ Classifier

• Authors: E. Świercz
• Languages of publication: EN

Abstracts

EN

The paper presents a novel approach, based on the wavelet decomposition and the learning vector quantisation algorithm, to automatic classification of signals with linear frequency modulation, generated by radar emitters. The goal of radar transmitter classification is to determine the particular transmitter, from which a signal originated, using only the just received waveform. To categorise a current linear frequency modulation signal to the particular transmitter, the discrete wavelet decomposition of the received signal is accomplished in order to get a representative set of features with good classification properties. The learning vector quantisation algorithm with a previously defined set of features as an input of the learning vector quantisation neural net is proposed as the intelligent classification algorithm, which combines competitive learning with supervision. After the learning process, the learning vector quantisation algorithm is ready to perform the classification process for different data than data used in the learning stage. Simulation results show the high classification accuracy for experimentally chosen wavelets and suggested architecture of the learning vector quantisation classifier.

Keywords

EN

84.40.Ua; 84.35.+i

Discipline

• 84.35.+i: Neural networks(for optical neural networks, see 42.79.Ta; see also 07.05.Mh Neural networks, fuzzy logic, artificial intelligence in computers in experimental physics; 87.18.Sn in biological complexity)
• 84.40.Ua: Telecommunications: signal transmission and processing; communication satellites(for optical communications, see 42.79.Sz in optics)

• Publisher: Institute of Physics, Polish Academy of Sciences
• Journal: Acta Physica Polonica A
• Year: 2011
• Volume: 119
• Issue: 4
• Pages: 488-494

Dates

published

2011-04

Contributors

author

E. Świercz

• Faculty of Electrical Engineering, Białystok University of Technology, Wiejska 45D, 15-351 Białystok, Poland

References

• 1. J. Liu, J.P.Y Lee, L. Li, Z.-Q. Luo, K.M. Wong, IEEE Trans. Pattern Anal. Machine Intellig. 27, 1185 (2005)
• 2. M.-Q. Ren, Y.-Q. Zhu, Y. Mao, J. Han, in: Proc. 2007 Int. Conf. on Wavelet Analysis and Pattern Recognition, Beijing (China), University of Science and Technology, Beijing 2007, p. 1442
• 3. K. Kulpa, in: Proc. Int. Conf. on Radar, IEEE Cat. No.03EX695, Adelaide (Australia), 2003, p. 235
• 4. F. Auger, P. Flandrin, P. Goncalves, O. Lemoine, Time-Frequency Toolbox For Use with Matlab, CNRS, France, Rice University, USA, 1995-1996
• 5. E. Swiercz, in: Proc. XI Int. Radar Symp. IRS-2010, Vilnius (Lithuania), 2010, p. 599
• 6. Y. Al-Assaf, Comput. Industr. Eng. 47, 17 (2004)
• 7. E.D. Ubeyli, Expert Systems Appl. 34, 1954 (2008)
• 8. E. Swiercz, in: Computational Methods and Experimental Measurements XIV, Eds. C.A. Brebbia, G.M. Carlomagno, WIT Press, Southampton 2009, p. 271
• 9. M. Misiti, Y. Misiti, G. Oppenheim, J.-M. Poggi, Wavelet Toolbox For Use with MATLAB, The MathWorks, Inc., 24 Prime Park Way, Natick, MA 01760-1500, 1996-1997
• 10. L. Fausett, Fundamental of Neural Networks Architectures, Algorithms, and Applications, Prentice-Hall, Inc., Upper Saddle River, NJ 1994

Identifiers

DOI

10.12693/APhysPolA.119.488