Hybrid Noise-Resilient Deep Learning Architecture for Modulation Classification in Cognitive Radio Networks

  • Antoni IvanovEmail author
  • Krasimir Tonchev
  • Vladimir Poulkov
  • Hussein Al-Shatri
  • Anja Klein
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 283)


The increasing maturity of the concepts which would allow for the operation of a practical Cognitive Radio (CR) Network require functionalities derived through different methodologies from other fields. One such approach is Deep Learning (DL) which can be applied to diverse problems in CR to enhance its effectiveness by increasing the utilization of the unused radio spectrum. Using DL, the CR device can identify whether the signal comes from the Primary User (PU) transmitter or from an interferer. The method proposed in this paper is a hybrid DL architecture which aims at achieving high recognition rate at low signal-to-noise ratio (SNR) and various channel impairments including fading because such are the relevant conditions of operation of the CR. It consists of an autoencoder and a neural network structure due to the good denoising qualities of the former and the recognition accuracy of the latter. The autoencoder aims to restore the original signal from the corrupted samples which would increase the accuracy of the classifier. Afterwards its output is fed into the NN which learns the characteristics of each modulation type and classifies the restored signal correctly with certain probability. To determine the optimal classification DL model, several types of NN structures are examined and compared for input comprised of the IQ samples of the reconstructed signal. The performance of the proposed DL architecture in comparison to similar models for the relevant parameters in different channel impairments scenarios is also analyzed.


Cognitive Radio Deep Learning Modulation classification Spectrum sensing 



The paper is published with the support of the project No BG05M2OP001-2.009-0033 “Promotion of Contemporary Research Through Creation of Scientific and Innovative Environment to Encourage Young Researchers in Technical University - Sofia and The National Railway Infrastructure Company in The Field of Engineering Science and Technology Development” within the Intelligent Growth Science and Education Operational Programme co-funded by the European Structural and Investment Funds of the European Union.


  1. 1.
    Ali, A., Yangyu, F., Liu, S.: Automatic modulation classification of digital modulation signals with stacked autoencoders. Digit. Signal Process. 71, 108–116 (2017)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Arumugam, K.S.K., Kadampot, I.A., Tahmasbi, M., Shah, S., Bloch, M., Pokutta, S.: Modulation recognition using side information and hybrid learning. In: 2017 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), pp. 1–2. IEEE (2017)Google Scholar
  3. 3.
    Bhatti, S.A., et al.: Impulsive noise modelling and prediction of its impact on the performance of WLAN receiver. In: 2009 17th European Signal Processing Conference, pp. 1680–1684. IEEE (2009)Google Scholar
  4. 4.
    Dobre, O.A., Abdi, A., Bar-Ness, Y., Su, W.: Blind modulation classification: a concept whose time has come. In: 2005 IEEE/Sarnoff Symposium on Advances in Wired and Wireless Communication, pp. 223–228. IEEE (2005)Google Scholar
  5. 5.
    Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016).
  6. 6.
    Gouldieff, V., Palicot, J., Daumont, S.: Blind automatic modulation classification in multipath fading channels. In: 2017 22nd International Conference on Digital Signal Processing (DSP), pp. 1–5. IEEE (2017)Google Scholar
  7. 7.
    Gurugopinath, S.: Energy-based bayesian spectrum sensing over \(\alpha \)-\(\mu \)/stacy/generalized gamma fading channels. In: 2016 8th International Conference on Communication Systems and Networks (COMSNETS), pp. 1–6. IEEE (2016)Google Scholar
  8. 8.
    Gurugopinath, S., Muralishankar, R., Shankar, H.: Spectrum sensing in the presence of cauchy noise through differential entropy. In: Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER), pp. 201–204. IEEE (2016)Google Scholar
  9. 9.
    Hong, D., Zhang, Z., Xu, X.: Automatic modulation classification using recurrent neural networks. In: 2017 3rd IEEE International Conference on Computer and Communications (ICCC), pp. 695–700. IEEE (2017)Google Scholar
  10. 10.
    Ivanov, A., Mihovska, A., Tonchev, K., Poulkov, V.: Real-time adaptive spectrum sensing for cyclostationary and energy detectors. IEEE Aerosp. Electron. Syst. Mag. 33(5–6), 20–33 (2018). Scholar
  11. 11.
    Jang, W.M.: Blind cyclostationary spectrum sensing in cognitive radios. IEEE Commun. Lett. 18(3), 393–396 (2014)CrossRefGoogle Scholar
  12. 12.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  13. 13.
    Lee, J.H., Kim, J., Kim, B., Yoon, D., Choi, J.W.: Robust automatic modulation classification technique for fading channels via deep neural network. Entropy 19(9) (2017).,
  14. 14.
    Li, S., Li, W., Cook, C., Zhu, C., Gao, Y.: Independently recurrent neural network (IndRNN): building a longer and deeper RNN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5457–5466 (2018)Google Scholar
  15. 15.
    Loshchilov, I., Hutter, F.: Fixing weight decay regularization in adam. arXiv preprint arXiv:1711.05101 (2017)
  16. 16.
    Mendis, G.J., Wei, J., Madanayake, A.: Deep learning-based automated modulation classification for cognitive radio. In: 2016 IEEE International Conference on Communication Systems (ICCS), pp. 1–6. IEEE (2016)Google Scholar
  17. 17.
    Orlic, V.D., Dukic, M.L.: Automatic modulation classification: sixth-order cumulant features as a solution for real-world challenges. In: 2012 20th Telecommunications Forum (TELFOR), pp. 392–399. IEEE (2012)Google Scholar
  18. 18.
    O’Shea, T.J., Corgan, J., Clancy, T.C.: Convolutional radio modulation recognition networks. In: Jayne, C., Iliadis, L. (eds.) EANN 2016. CCIS, vol. 629, pp. 213–226. Springer, Cham (2016). Scholar
  19. 19.
    O’Shea, T.J., Roy, T., Clancy, T.C.: Over-the-air deep learning based radio signal classification. IEEE J. Sel. Top. Signal Process. 12(1), 168–179 (2018)CrossRefGoogle Scholar
  20. 20.
    Peng, S., Jiang, H., Wang, H., Alwageed, H., Yao, Y.D.: Modulation classification using convolutional neural network based deep learning model. In: 2017 26th Wireless and Optical Communication Conference (WOCC), pp. 1–5. IEEE (2017)Google Scholar
  21. 21.
    Qing Yang, G.: Modulation classification based on extensible neural networks. Math. Probl. Eng. 2017 (2017) CrossRefGoogle Scholar
  22. 22.
    Rajendran, S., Meert, W., Giustiniano, D., Lenders, V., Pollin, S.: Distributed deep learning models for wireless signal classification with low-cost spectrum sensors. arXiv preprint arXiv:1707.08908 (2017)
  23. 23.
    Smith, S.L., Kindermans, P.J., Le, Q.V.: Don’t decay the learning rate, increase the batch size. arXiv preprint arXiv:1711.00489 (2017)
  24. 24.
    Spaulding, A., Middleton, D.: Optimum reception in an impulsive interference environment - Part I: coherent detection. IEEE Trans. Commun. 25(9), 910–923 (1977). Scholar
  25. 25.
    Stevenson, C.R., Chouinard, G., Lei, Z., Hu, W., Shellhammer, S.J., Caldwell, W.: IEEE 802.22: the first cognitive radio wireless regional area network standard. IEEE Commun. Mag. 47(1), 130–138 (2009)CrossRefGoogle Scholar
  26. 26.
    The GNU Radio Foundation: GNU Radio, the free and open software radio ecosystem, October 2018.
  27. 27.
    Tsakalides, P., Nikias, C.L.: Maximum likelihood localization of sources in noise modeled as a stable process. IEEE Trans. Signal Process. 43(11), 2700–2713 (1995)CrossRefGoogle Scholar
  28. 28.
    Xiong, X., Feng, J., Jiang, L.: Automatic digital modulation classification for ors satellite relay communication. In: 2015 International Conference on Wireless Communications & Signal Processing (WCSP), pp. 1–5. IEEE (2015)Google Scholar
  29. 29.
    Xu, J.L., Su, W., Zhou, M.: Likelihood-ratio approaches to automatic modulation classification. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 41(4), 455–469 (2011)CrossRefGoogle Scholar
  30. 30.
    Xu, Y., Li, D., Wang, Z., Guo, Q., Xiang, W.: A deep learning method based on convolutional neural network for automatic modulation classification of wireless signals. Wireless Networks. Springer, New York (2017). Scholar
  31. 31.
    Zhang, D., et al.: Automatic modulation classification based on deep learning for unmanned aerial vehicles. Sensors 18(3), 924 (2018)CrossRefGoogle Scholar
  32. 32.
    Zhang, Z., Hua, Z., Liu, Y.: Modulation classification in multipath fading channels using sixth-order cumulants and stacked convolutional auto-encoders. Wirel. Netw. 11(6), 910–915 (2017)Google Scholar
  33. 33.
    Zhu, X., Fujii, T.: A novel modulation classification method in cognitive radios using higher-order cumulants and denoising stacked sparse autoencoder. In: 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), pp. 1–5, December 2016.

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2019

Authors and Affiliations

  • Antoni Ivanov
    • 1
    Email author
  • Krasimir Tonchev
    • 1
  • Vladimir Poulkov
    • 1
  • Hussein Al-Shatri
    • 2
  • Anja Klein
    • 2
  1. 1.Faculty of TelecommunicationsTechnical University of SofiaSofiaBulgaria
  2. 2.Department of Electrical Engineering and Information TechnologyTechnical University DarmstadtDarmstadtGermany

Personalised recommendations