ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Ensemble convolutional neural networks for automatic fusion recognition of multi-platform radar emitters

  • Zhou, Zhiwen (Department of Operational Command, Command College of the PAP) ;
  • Huang, Gaoming (College of Electronic Engineering, Naval University of Engineering) ;
  • Wang, Xuebao (College of Electronic Engineering, Naval University of Engineering)
  • Received : 2017.12.17
  • Accepted : 2019.04.07
  • Published : 2019.12.06
Download PDF
⟨ Previous Next ⟩

Abstract

Presently, the extraction of hand-crafted features is still the dominant method in radar emitter recognition. To solve the complicated problems of selection and updation of empirical features, we present a novel automatic feature extraction structure based on deep learning. In particular, a convolutional neural network (CNN) is adopted to extract high-level abstract representations from the time-frequency images of emitter signals. Thus, the redundant process of designing discriminative features can be avoided. Furthermore, to address the performance degradation of a single platform, we propose the construction of an ensemble learning-based architecture for multi-platform fusion recognition. Experimental results indicate that the proposed algorithms are feasible and effective, and they outperform other typical feature extraction and fusion recognition methods in terms of accuracy. Moreover, the proposed structure could be extended to other prevalent ensemble learning alternatives.

Keywords

References

  1. R.G. Wiley, ELINT: The interception and analysis of radar signals, Artech House Publishers, London, USA, 2006.
  2. Q. Guo et al., Recognition of radar emitter signals based on SVD and AF main ridge slice, J. Commun. Netw. 17 (2015), no. 5, 491-498. https://doi.org/10.1109/JCN.2015.000087
  3. D. Zeng et al., Automatic modulation classification of radar signals using the generalized time-frequency fepresentation of Zhao, Atlas and Marks, IET Radar, Sonar Navig. 5 (2010), no. 4, 507-516. https://doi.org/10.1049/iet-rsn.2010.0174
  4. J. Ma et al., Robust radar waveform recognition algorithm based on random projections and sparse classification, IET Radar Sonar Navig. 8 (2014), no. 4, 290-296. https://doi.org/10.1049/iet-rsn.2013.0088
  5. C. Andre, S.L. Hegarat-Mascle, and R. Reynaud, Evidential framework for data fusion in a multi-sensor surveillance system, Eng. Appl. Artif. Intell. 43 (2015), 166-180. https://doi.org/10.1016/j.engappai.2015.04.012
  6. Z.W. Zhou, G.M. Huang, and J. Gao, An emitter fusion recognition algorithm based on multi-collaborative representation, in Proc. Int. Cong. Image Signal Process, Liaoning, China, 2015, pp. 1231-1235.
  7. C.X. Chen, M.H. He, and H.F. Li, An improved radar emitter recognition method based on Dezert-Smarandache theory, Chinese J. Electron. 24 (2015), no. 3, 611-615. https://doi.org/10.1049/cje.2015.07.029
  8. Y. Bengio, Learning Deep Architectures for AI: Foundations and Trends in Machine Learning, Now Publishers, USA, 2009.
  9. J. Schmidhuber, Deep learning in neural networks: an overview, Neural Netw. 61 (2015), 85-117. https://doi.org/10.1016/j.neunet.2014.09.003
  10. X.B. Wang et al., Radar emitter recognition based on the short time fourier transform and convolutional neural networks, in Proc. Int. Cong. Image Signal Process., BioMed. Eng. Inform., Shanghai, China, 2017, pp. 1-5.
  11. C. Wang, J. Wang, and X.D. Zhang, Automatic radar waveform recognition based on time-frequency analysis and convolutional neural network, in Proc. Int. Conf. Acoust., Speech, Signal Process., New Orleans, LA, USA, 2017, pp. 2437-2441.
  12. S.H. Kong et al., Automatic LPI radar waveform recognition using CNN, IEEE Access 6 (2018), 4207-4219. https://doi.org/10.1109/ACCESS.2017.2788942
  13. M. Skurichina and R.P.W. Duin, Bagging, boosting and the random subspace method for linear classifiers, Pattern Anal. Appl. 5 (2002), no. 2, 121-135. https://doi.org/10.1007/s100440200011
  14. Y. Freund, Boosting a weak learning algorithm by majority, Inf. Comput. 121 (1995), no. 2, 256-285. https://doi.org/10.1006/inco.1995.1136
  15. T. Thayaparan et al., Time-frequency approach to radar detection, imaging, and classification, IET Signal Process. 4 (2010), no. 4, 325-328. https://doi.org/10.1049/iet-spr.2010.9095
  16. R. Moradi and R. Yousefzadeh, Recognizing objectionable images using convolutional neural nets, in Proc. Signal Process. Intell. Sys. Conf., Tehran, Iran, 2015, pp. 133-137.
  17. M. Anthimopoulos et al., Lung pattern classification for interstitial lung diseases using a deep convolutional neural network, IEEE Trans. Med. Imaging 35 (2016), no. 5, 1207-1216. https://doi.org/10.1109/TMI.2016.2535865
  18. Y. Freund and R.E. Schapire, A decision-theoretic generalization of on-line learning and an application to boosting, Lecture Notes Comput. Sci. 55 (1999), 23-37.
  19. L. Breiman, Bagging predictors, Mach. Learn. 24 (1996), no. 2, 123-140. https://doi.org/10.1007/BF00058655
  20. D.C. Tao et al., Asymmetric bagging and random subspace for support vector machines-based relevance feedback in image retrieval, IEEE Trans. Pattern Anal. Mach. Intell. 28 (2006), no. 7, 1088-1099. https://doi.org/10.1109/TPAMI.2006.134
  21. J. Lunden and V. Koivunen, Automatic radar waveform recognition, IEEE J. Sel. Top Signal Process. 1 (2007), no. 1, 124-136. https://doi.org/10.1109/JSTSP.2007.897055