作者中心
专家审稿
责编办公
编辑办公
Radar Emitter Signal Identification Based on Weighted Normalized Singular-value Decomposition
-
摘要: 随着现代技术不断更新，雷达种类及相关技术得到不断发展，雷达辐射源信号的识别逐渐成为一个十分重要的研究领域。该文主要针对辐射源信号识别中的调制类型识别问题，从数据能量角度出发，在奇异值分解(Singular Value Decomposition, SVD)基础上进行优化，提出基于权重归一化奇异值分解特征提取算法。该文从奇异值分解的滤波效果、数据矩阵行数对分解结果的影响及不同分类模型识别效果等方面进行分析。实验结果表明该算法对常用雷达信号有较好滤波和识别效果，在–20 dB条件下滤波重构信号与原始信号余弦相似度值仍保持在0.94左右，在判别置信度
$\alpha $ 为0.65条件下识别正确率仍维持在97%以上。此外实验还表明相对于传统PCA算法，基于权重归一化奇异值分解特征提取算法拥有更好的鲁棒性。Abstract: With the continuous advancement of modern technology, more types of radar and related technologies are continuously being developed, and the identification of radar emitter signals has gradually become a very important research field. This paper focuses on the identification of modulation types in radar emitter signal identification. We propose a weighted normalized Singular-Value Decomposition (SVD) feature extraction algorithm, which is based on the perspective of data energy and SVD. The filtering effect of complex SVD is analyzed, as well as the influence of the number of rows of data matrix on the decomposition results, and the recognition effect of different classification models. The experimental results show that the algorithm has better filtering and recognition effects on common radar signals. Under –20 dB, the cosine similarity values of the reconstructed and original signals remain at about 0.94, and the recognition accuracy remains above 97% under a confidence level$\alpha $ of 0.65. In addition, experiments show that the weighted normalized SVD feature extraction algorithm has better robustness than the traditional Principal Component Analysis (PCA) algorithm. -
图 3 权重归一化奇异值特征提取示意图
Figure 3. Weighted normalized singular value feature extraction schematic
图 5 奇异值分解滤波重构信号及加噪信号与原始信号的欧式距离相似度对比示意图
Figure 5. Schematic diagram of the Euclidean distanceof the reconstructed signal and the noisy signal with the original signal with the signal-to-noise ratio
图 6 奇异值分解滤波重构信号及加噪信号与原始信号的余弦相似度随信噪比变化示意图
Figure 6. Schematic diagram of the cosine similarity of the singular value decomposition filter reconstructed signal and of the original signal with the signal-to-noise ratio
图 7 数据矩阵行数对奇异值分解重构信号与原始信号欧氏距离影响示意图
Figure 7. Schematic diagram of the influence of the number of rows of data matrix on the singular value decomposition reconstructed signal and the original signal Euclidean distance
图 8 数据矩阵行数对奇异值分解重构信号与原始信号余弦相似度影响示意图
Figure 8. Schematic diagram of the influence of the number of rows of data matrix on the singular value decomposition reconstructed signal and the cosine similarity of the original signal
图 9 辐射源信号识别模型的训练流程图
Figure 9. Radiation source identification model training flowchart
图 10 WN-SVD算法和PCA算法在不同分类模型识别结果随信噪比变化图
Figure 10. The change chart of recognition results based on different classification models and SNR
图 11 信号基于权重归一化奇异值分解特征提取方法在不同判别参数条件下准确率分布图
Figure 11. Signals based on weighted normalized singular value decomposition feature extraction method for accuracy rate distribution under different discriminant parameters
图 12 信号基于PCA特征提取方法在不同判别参数条件下准确率分布图
Figure 12. Signal accuracy distribution based on PCA feature extraction method under different discriminant parameters
图 13 判别参数
$\alpha $ =0.85时4类信号在不同信噪比条件下准确率分布图Figure 13. The accuracy rate distribution chart for four types of signals with different signal-to-noise ratio when discriminating parameter
$\alpha $ =0.85 -
[1] DE CARVALHO E, DENEIRE L, and SLOCK D T M. Blind and semi-blind maximum likelihood techniques for multiuser multichannel identification[C]. Proceedings of the 9th European Signal Processing Conference (EUSIPCO 1998), Rhodes, 1998: 1–4. [2] KANTERAKIS E and SU W. OFDM signal classification in frequency selective Rayleigh channels[C]. Proceedings of MILCOM 2011 Military Communications Conference, Baltimore, MD, 2011: 1–6. [3] XU J L, SU W, and ZHOU M C. Likelihood-ratio approaches to automatic modulation classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) , 2011, 41(4): 455–469. doi: 10.1109/TSMCC.2010.2076347 [4] SALAM A O A, SHERIFF R E, AL-ARAJI S R, et al. Automatic modulation classification in cognitive radio using multiple antennas and maximum-likelihood techniques[C]. Proceedings of 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing, Liverpool, 2015: 1–5. [5] PUNITH KUMAR H L and SHRINIVASAN L. Automatic digital modulation recognition using minimum feature extraction[C]. Proceedings of the 2nd International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India, 2015: 772–775. [6] BAGGA J and TRIPATHI N. Analysis of digitally modulated signals using instantaneous and stochastic features for classification[J]. International Journal of Soft Computing and Engineering (IJSCE) , 2011, 1(2): 57–61. [7] CHENG Y Z, ZHANG H L, and WANG Y. Research on modulation recognition of the communication signal based on statistical model[C]. Proceedings of the 3rd International Conference on Measuring Technology and Mechatronics Automation, Shanghai, 2011: 46–50. [8] WANG L and REN Y. Recognition of digital modulation signals based on high order cumulants and support vector machines[C]. 2009 ISECS International Colloquium on Computing, Communication, Control, and Management, Sanya, 2009: 271–274. [9] SHAKRA M M, SHAHEEN E M, BAKR H A, et al. C3. automatic digital modulation recognition of satellite communication signals[C]. Proceedings of the 32nd National Radio Science Conference (NRSC), 6th of October City, 2015: 118–126. [10] HASSANPOUR S, PEZESHK A M, and BEHNIA F. Automatic digital modulation recognition based on novel features and support vector machine[C]. Proceedings of the 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), Naples, 2016: 172–177. [11] EBRAHIMZADEH A and GHAZALIAN R. Blind digital modulation classification in software radio using the optimized classifier and feature subset selection[J]. Engineering Applications of Artificial Intelligence, 2011, 24(1): 50–59. doi: 10.1016/j.engappai.2010.08.008 [12] SUN G C, AN J P, YANG J, et al. A new key features extraction algorithm for automatic digital modulation recognition[C]. Proceedings of 2007 International Conference on Wireless Communications, Networking and Mobile Computing, Shanghai, 2007: 2306–2309. [13] LI S P, CHEN F C, and WANG L. Modulation recognition algorithm of digital signal based on support vector machine[C]. Proceedings of the 24th Chinese Control and Decision Conference (CCDC), Taiyuan, 2012: 3326–3330. [14] AMOEDO D A, DA SILVA JÚNIOR W S, and DE LIMA FILHO E B. Parameter selection for SVM in automatic modulation classification of analog and digital signals[C]. Proceedings of 2014 International Telecommunications Symposium (ITS), Sao Paulo, 2014: 1–5. [15] HASSAN K, DAYOUB I, HAMOUDA W, et al. Automatic modulation recognition using wavelet transform and neural networks in wireless systems[J]. EURASIP Journal on Advances in Signal Processing, 2010, 2010: 532898. doi: 10.1155/2010/532898 [16] GUESMI L and MENIF M. Modulation formats recognition technique using artificial neural networks for radio over fiber systems[C]. Proceedings of the 17th International Conference on Transparent Optical Networks (ICTON), Budapest, 2015: 1–4. [17] ZHAO Z J and GU J W. Recognition of digital modulation signals based on hybrid three-order restricted Boltzmann machine[C]. Proceedings of the IEEE 16th International Conference on Communication Technology (ICCT), Hangzhou, 2015: 166–169. [18] PATIL N M and NEMADE M U. Audio signal deblurring using singular value decomposition (SVD)[C]. Proceedings of 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI), Chennai, India, 2017: 1272–1276. [19] YE W B, LI S T, ZHAO X J, et al. A K times singular value decomposition based image denoising algorithm for DoFP polarization image sensors with Gaussian noise[J]. IEEE Sensors Journal, 2018, 18(15): 6138–6144. doi: 10.1109/JSEN.2018.2846672 [20] TANIN U H, JAHAN A, SHARMIN S, et al. De-noised and compressed image watermarking based on singular value decomposition[C]. Proceedings of 2017 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), Dhaka, 2017: 628–633. [21] KABIR S S, RIZVE M N, and HASAN M K. ECG signal compression using data extraction and truncated singular value decomposition[C]. Proceedings of 2017 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), Dhaka, 2017: 5–7. [22] ZHANG X N, LUO P C, and HU X W. A hybrid method for classification and identification of emitter signals[C]. Proceedings of 4th International Conference on Systems and Informatics (ICSAI), Hangzhou, 2017: 1060–1065. -
下载:
计量
- 文章访问数: 2545
- HTML全文浏览量: 729
- PDF下载量: 201
- 被引次数: 0
