A Modulation Recognition Method Based on Bispectrum and DNN

  • Jiang Yu
  • Zunwen HeEmail author
  • Yan Zhang
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 516)


In this paper, we propose a new method for modulation recognition of received digital signals using bispectrum and AlexNet. The bispectrum analysis is used to generate the feature images, AlexNet, as a widely used deep neural network (DNN), is used as the classifier. It is able to classify six common digital communication signals, including 2ASK, 4ASK, 2FSK, 4FSK, 2PSK and 4PSK. Compared to the traditional decision-theoretic methods, the proposed method needs no prior information for the received signals. The numerical results indicate that this method is more robust and effective than the classical decision theory and its improved algorithm, particularly when the signal-to-noise ratio (SNR) is low. It is shown that the success rate of 90% can be achieved when the SNR is greater than or equal to 3 dB.


AlexNet Bispectrum CNN DNN Modulation recognition 



This work was supported in part by National Nature Science Foundation of China under Grants No. 61201192 and the National High Technology Research and Development Program of China under Grants No. 2015AA01A708.


  1. 1.
    Azzouz EE, Nandi AK. Algorithms for automatic modulation recognition of communication signals. IEEE Trans Commun. 1998;46(4):431–6.CrossRefGoogle Scholar
  2. 2.
    Dobre OA, Abdi A, Bar-Ness Y, et al. A survey of automatic modulation classification techniques: classical approaches and new trends. IET Comm. 2007;1(2):137–56.CrossRefGoogle Scholar
  3. 3.
    Wong MLD, Nandi AK. Automatic digital modulation recognition using artificial neural network and genetic algorithm. Sig Process. 2004;84(2):351–65.CrossRefGoogle Scholar
  4. 4.
    Park CS, Kim DY. Modulation classification of analog and digital signals using neural network and support vector machine. In: 4th international symposium on neural networks, ICNN2007, Nanjing, Jun 2007.Google Scholar
  5. 5.
    Lopatka J, Pedzisz M. Automatic modulation classification using statistical moments and a fuzzy classifier. In: International conference on signal processing, vol. 3, 61(24); 2000. p. 1500–6.Google Scholar
  6. 6.
    Ebrahimzadeh A, Ardeshir GR. A new signal type classifier for fading environments. J Comp Info Technol. 2007;15(3):257–66.CrossRefGoogle Scholar
  7. 7.
    Wong MDL, Nandi AK. Efficacies of selected blind modulation type detection methods for adaptive OFDM systems. In: Proceedings of the international conference on signal processing and communication systems, ISCPSC2007; Dec 2007.Google Scholar
  8. 8.
    Liu J, Luo Q. A novel modulation classification algorithm based on daubechies5 wavelet and fractional fourier transform in cognitive radio. In: IEEE ICCT; 2012. p. 115–20.Google Scholar
  9. 9.
    Li D, Yu D. Deep learning: methods and applications. Found Trends Sig Process. 2014;7(3–4):197–387.MathSciNetCrossRefGoogle Scholar
  10. 10.
    Nikias CL, Mendel JM. Signal processing with higher-order spectra. IEEE Sig Process Mag. 1993;10(3):10–37.CrossRefGoogle Scholar
  11. 11.
    Lin Y, Tu Y, Dou Z et al. The application of deep learning in communication signal modulation recognition. In: 2017 IEEE/CIC international conference on communications in China (ICCC), Qingdao; Oct 2017.Google Scholar
  12. 12.
    Krizhevsky A, Sutskever I, Hinton G. ImageNet classification with deep convolutional neural networks. In: International conference on neural information processing systems, p. 1097–105 (2012).Google Scholar
  13. 13.
    Zhang DM, Wang X. Improved method of digital signals modulation identification based on decision theory. J Comput Appl. 2009;29(12):3227–30.Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.School of Information and ElectronicsBeijing Institute of TechnologyBeijingPeople’s Republic of China

Personalised recommendations