Radar emitter signal recognition based on ambiguity function contour lines and stacked denoising auto-encoders

被引：0
作者：
Pu Y. [1 ,2 ]
Guo J. [1 ]
Liu T. [1 ]
Wu H. [1 ]
机构：
[1] Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming
[2] Computing Center, Kunming University of Science and Technology, Kunming
来源：
Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument | 2021年 / 42卷 / 01期
关键词：
Ambiguity function; Deep learning; Radar emitter signal; Signal recognition; Stacked denoising auto-encoders;
D O I：
10.19650/j.cnki.cjsi.J2006953
中图分类号：
学科分类号：
摘要：
The complex radar emitter signal recognition methods have problems of poor anti-noise performance, low recognition rate, etc. To address these issues, we propose a new recognition method based on ambiguity function contour lines and stacked denoising auto-encoders. First, the ambiguity function is processed by the Gaussian smoothing and the contour lines are calculated by linear interpolation. Then, principal component analysis is used to reduce its feature dimension. The main ambiguity energy information is remained. Finally, deep learning stacked denoising auto-encoders are established to learn and extract the deep and more ubiquitous features of contour lines. The Softmax classifier is used to classify them. Simulation experiments show that the overall average recognition rates of six types of typical radar signals are all above 99.83% when the signal-noise ratio is 0 dB. The recognition rate can also reach 83.67% when the signal-noise ratio is -6 dB. Results prove that this method has good performance and feasibility under the extremely low signal-noise ratio conditions. © 2021, Science Press. All right reserved.
引用
收藏
页码：207 / 216
页数：9
相关论文
共 19 条
  • [1] DELPART N., Asymptotic wavelet and Gabor analysis: Extraction of instantaneous frequencies, IEEE Trans. Information Theory, 38, 3, pp. 644-664, (1992)
  • [2] MORAITAKIS I, FARGUES M P., Feature extraction of intra-pulse modulated signals using time-frequency analysis, Proceedings of 21st Century Military Communications Conference, pp. 737-741, (2000)
  • [3] LOPEZ R G, GRAJAL J, YESTE O O., Atomic decomposition-based radar complex signal interception, Radar, Sonar and Navigation, IEE Proceedings, 150, 4, pp. 323-331, (2003)
  • [4] LONG Y, HE Y G, ZHANG ZH, Et al., Switched-current circuit fault diagnosis based on entropy and Haar wavelet transform, Chinese Journal of Scientific Instrument, 36, 3, pp. 701-711, (2015)
  • [5] CHEN CH X, HE M H, XU J, Et al., A new method for sorting unknown radar emitter signal, Chinese Journal of Electronics, 23, 3, pp. 499-502, (2014)
  • [6] CAO R, CAO J W, MEI J P, Et al., Radar emitter identification with bispectrum and hierarchical extreme learning machine, Multimedia Tools and Applications, 78, 20, pp. 28953-28970, (2019)
  • [7] WANG J H, YANG Y X, MA CH., Wavelet ridge extraction algorithm using a cost function in two dimensional wavelet transform, Chinese Journal of Scientific Instrument, 38, 12, pp. 2915-2923, (2017)
  • [8] HAN J, HE M H, ZHU ZH B, Et al., Sorting unknown radar emitter signal based on the complexity characteristics, Journal of Electronics & Information technology, 31, 11, pp. 2552-2556, (2009)
  • [9] GUO Q, NAN P L, ZHANG X Y, Et al., Recognition of radar emitter signals based on SVD and AF main ridge slice, IEEE Journals & Magazines, Journal of Communications & Networks, 17, 5, pp. 491-498, (2015)
  • [10] ZHU Y G, LIU R M, HUANG Q T., Fine-grained image recognition of weak supervisory information based on deep neural network, Journal of Electronic Measurement and Instrumentation, 34, 2, pp. 115-122, (2020)
12