Advertisement

Radio Fingerprint Extraction Based on Marginal Fisher Deep Autoencoders

  • Jian-hang Huang
  • Ying-ke Lei
Article

Abstract

Aiming at the difficulty of extracting radio fingerprint feature caused by insufficient traditional training method under small labeled sample prerequisite, the deep autoencoders regularized by marginal Fisher analysis algorithm for radio fingerprint extraction is proposed. Based on deep autoencoders, the training procedures was divided into two parts: unsupervised pre-training and supervised finetuning based on marginal Fisher analysis. In the algorithm, firstly the individual information of radio classes in large amounts of unlabeled signal samples was extracted, whose information was then applied on model optimal parameters learning by deep autoencoders. Then the trainable parameters were analyzed by marginal Fisher method with the assistant of labeled samples to improve the discriminant capability of fingerprint feature between radio individuals of the same model. The classification experiment was operated on several communication radio signal dataset. The results proved that the differences of radio individuals of the same model can be represented effectively through the algorithm proposed.

Keywords

Small sample condition Radio fingerprint Autoencoders Marginal Fisher analysis 

Notes

Acknowledgements

This work is supported by the grants of the National Science Foundation of China, No. 61272333. The authors would like to thank all the guest editors and anonymous reviewers for their constructive advices.

References

  1. 1.
    Liu, Z. (2005). Research on modulation classification and individual identification of emitters. Doctor’s dissertation, National University of Defense Technology.Google Scholar
  2. 2.
    Tang, Z., & Lei, Y. K. (2016). Algorithm of maximum correntropy based on l 2-regularization in individual communication transmitter identification. Pattern Recognition and Artificial Intelligence, 29(6), 527–533.Google Scholar
  3. 3.
    Cai, Z. W., & Li, J. D. (2007). Study of transmitter individual identification based on bispectra. Journal of Communications, 28(2), 75–79.Google Scholar
  4. 4.
    Huang, X., & Guo, H. W. (2015). A robust specific communication emitter identification method. Telecommunication Engineering, 55(3), 321–327.Google Scholar
  5. 5.
    Tang, Z. L. (2013). A study of nonlinear method for specific communications emitter identifications. Doctor’s dissertation, Xidian University.Google Scholar
  6. 6.
    Gui, Y. C., Yang, J. A., & Lv, J. J. (2017). Feature extraction algorithm based on intrinsic time-scale decomposition model for communication transmitter. Application Research of Computers, 4, 1172–1175.Google Scholar
  7. 7.
    Chen, Z. W., Xu, Z. J., Wang, J. M., Xu, Y. L., & Kong, L. (2013). Emitter identification method based on cyclic spectrum density slice. Journal of Data Acquisition and Processing, 28(3), 284–288.Google Scholar
  8. 8.
    Lecun, Yann, Bengio, Yoshua, & Hinton, Geoffrey. (2015). Deep learning. Nature, 521(7553), 436–444.CrossRefGoogle Scholar
  9. 9.
    Ma, Y., & Bao, C. C. (2015). Speaker segmentation based on sparse neural network. Journal of Beijing University of Technology, 41(5), 662–667.MathSciNetGoogle Scholar
  10. 10.
    Chen, M. M. Killian, W., Sha, F., & Bengio, Y. (2014). Marginalized denoising auto-encoders for nonlinear representations. In Proceedings of the 2014 31th international conference on machine learning (pp. 1476–1484).Google Scholar
  11. 11.
    Zhang, Y., & Peng, H. (2017). One sample per person face recognition based on deep autoencoder. Pattern Recognition and Artificial Intelligence, 41(5), 662–667.Google Scholar
  12. 12.
    Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2006). Learning optimization greedy layer-wise training of deep networks. In Advances on neural information processing system (pp. 153–160).Google Scholar
  13. 13.
    Hinton, G. (2006). Reducing the dimensionality of data with neural network. Science, 313, 504–507.MathSciNetCrossRefGoogle Scholar
  14. 14.
    Yan, S. C., Xu, B. Y., Zhang, H. J., Yang, Q., & Lin, S. (2007). Graph embedding and extensions: A general framework for dimensionality reduction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(1), 40–51.CrossRefGoogle Scholar
  15. 15.
    Sun, Z. J., Xue, L., & Xu, Y. M. (2013). Marginal Fisher feature extraction algorithm based on deep learning. Journal of Electronics and Information Technology, 35(4), 805–811.CrossRefGoogle Scholar
  16. 16.
    Nocedal, Jorge. (1980). Updating quasi-newton matrices with limited storage. Mathematics of Computation, 35(151), 773–782.MathSciNetCrossRefGoogle Scholar
  17. 17.
    Xu, S. H., Huang, B. X., & Xu, L. N. (2008). Identificaion of individual radio transmitters using SIB/PCA. Journal of Huazhong University of Science and Technology (Natural Science Edition), 36(7), 14–17.Google Scholar
  18. 18.
    Xu, S. H., Xu, L. N., Xu, Z. G., & Huang, B. X. (2008). Individual radio transmitter identification based on spurious modulation characteristic of signal envelop. In IEEE transactions on military communications conference (pp. 1–5).Google Scholar
  19. 19.
    Wu, Z. Z., Takaki, S., & Yamagishi, J. (2015). Deep denoising auto-encoder for statistical speech synthesis. arXiv:1506.05268.

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.National University of Defense TechnologyHefeiThe People’s Republic of China

Personalised recommendations