Radar emitter signal recognition based on multi-scale wavelet entropy and feature weighting

Abstract

In modern electromagnetic environment, radar emitter signal recognition is an important research topic. On the basis of multi-resolution wavelet analysis, an adaptive radar emitter signal recognition method based on multi-scale wavelet entropy feature extraction and feature weighting was proposed. With the only priori knowledge of signal to noise ratio (SNR), the method of extracting multi-scale wavelet entropy features of wavelet coefficients from different received signals were combined with calculating uneven weight factor and stability weight factor of the extracted multi-dimensional characteristics. Radar emitter signals of different modulation types and different parameters modulated were recognized through feature weighting and feature fusion. Theoretical analysis and simulation results show that the presented algorithm has a high recognition rate. Additionally, when the SNR is greater than -4 dB, the correct recognition rate is higher than 93%. Hence, the proposed algorithm has great application value.

Keywords

emitter recognition / multi-scale wavelet entropy / feature weighting / uneven weight factor / stability weight factor

References

[1] KawalecA, OwczarekR. Radar emitter recognition using intrapulse data [C]. 15th International Conference on Microwaves, Radar and Wireless Communications. Mikon, 2004435-438

[2] DingJ, LiuZ-cheng. A study of radar emitter recognition based on characteristic parameter matching method [J]. Modern Radar, 2011, 33(9): 29-33

[3] XuH-q, LiuG. Reviews on radar emitter recognition [J]. Ship Electronic Engineering, 2010, 30(4): 25-27

[4] LuM-j, ZhanY, SiX-c, YangX-niu. Individual identification of 2FSK signal based on fine feature analysis of instantaneous frequency [J]. Systems Engineering and Electronics, 2009, 31(5): 1043-1046

[5] YuZ-b, ChenC-x, JinW-dong. Radar emitter signal recognition based on fusion entropy features [J]. Modern Radar, 2010, 32(1): 34-38

[6] ZhangG-x, HuL-z, JinW-dong. Radar emitter signal recognition based on entropy features [J]. Chinese Journal of Radio Science, 2005, 20(4): 440-445

[7] JiangS-f, FuC, WuZ-qi. Intelligent data-fusion model using correlation fractal dimension for structural damage identification [J]. Smart Materials and Intelligent Systems, 2011, 143(8): 1300-1304

[8] HuangJ-y, PanH-x, BiS-hua. Bi-spectrum entropy feature extraction and its application for fault diagnosis of gearbox [C]. Proceedings of 2010 IEEE International Conference on Fuzzy Systems. Taiwan, 20101-6

[9] WangY-e, ZhangT-q, BaiJ, BaoRui. Modulation identification algorithms for communication signals based on particle swarm optimization and support vector machines [J]. Transmitting and Receiving, 2011, 35(23): 106-110

[10] RenM-q, CaiJ-y, ZhuY-q, HeM-hao. Radar emitter signal classification based on mutul information and fuzzy support vector machines [C]. 9th International Conference on Signal Processing. Beijing, 20081641-1646

[11] YuD-j, YangY, ChengJ-sheng. Application of time-frequency entropy method based on Hilbert-Huang transform to gear fault diagnosis [J]. Measurement, 2007, 40(2): 823-830

[12] BercherJ F, VignatC. Estimating the entropy of a signal with applications [J]. IEEE Transactions on Signal Processing, 2000, 49(6): 1687-1694

[13] HamedM, NunoV. Cost-sensitive boosting [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(2): 294-309

[14] HanJ-w, KamberMData mining: Concepts and techniques [M], 20062nd edBeijing, China Machine Press: 289-326

[15] DavidR, NomanP, BeaulieuC. A comparison of SNR estimation techniques for the AWGN channel [J]. IEEE Transactions on Communications, 2000, 48(10): 1681-1691

[16] SuiD, GeL-dong. On the blind SNR estimation for IF signals [C]. Proceedings of the First International Conference on Innovative Computing, Information and Control. Beijing, 2006374-378

[17] JohannaV, HarriS, JanneL, Lehtomaki, MarkkuJ. A blind signal localization and SNR estimation method [C]. 2006 Military Communications Conference. Washington, DC, 20061-7

[18] ParkC, ChoiJ, NahS, JangW. Automatic recognition of digital signals using wavelet features and SVM [C]. 10th International Conference on Advanced Communication Technology. Gangwon-Do, 2008387-390