[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content
Springer Nature Link
Log in

Spectrum interference-based two-level data augmentation method in deep learning for automatic modulation classification

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Automatic modulation classification is an essential and challenging topic in the development of cognitive radios, and it is the cornerstone of adaptive modulation and demodulation abilities to sense and learn surrounding environments and make corresponding decisions. In this paper, we propose a spectrum interference-based two-level data augmentation method in deep learning for automatic modulation classification. Since the frequency variation over time is the most important distinction between radio signals with various modulation schemes, we plan to expand samples by introducing different intensities of interference to the spectrum of radio signals. The original signal is first transformed into the frequency domain by using short-time Fourier transform, and the interference to the spectrum can be realized by bidirectional noise masks that satisfy the specific distribution. The augmented signals can be reconstructed through inverse Fourier transform based on the interfered spectrum, and then, the original and augmented signals are fed into the network. Finally, data augmentation at both training and testing stages can be used to improve the generalization performance of deep neural network. To the best of our knowledge, this is the first time that radio signals are augmented to help modulation classification by considering the frequency domain information. Moreover, we have proved that data augmentation at the test stage can be interpreted as model ensemble. By comparing with a variety of data augmentation techniques and state-of-the-art modulation classification methods on the public dataset RadioML 2016.10a, experimental results illustrate the effectiveness and advancement of proposed method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Availability of data and materials

All experimental datasets during the study are available online (https://www.deepsig.io/datasets) and have been cited in the paper.

References

  1. Li P (2020) Research on radar signal recognition based on automatic machine learning. Neural Comput Appl 32(7):1959–1969

    Google Scholar 

  2. Chen Y (2019) A DDS-based wait-free phase-continuous carrier frequency modulation strategy for EMI reduction in FPGA-based motor drive. IEEE Trans Power Electron 34(10):9619–9631

    Google Scholar 

  3. Shu F et al (2017) Secure precise wireless transmission with random-subcarrier-selection-based directional modulation transmit antenna array. IEEE J Sel Areas Commun 36(4):890–904

    Google Scholar 

  4. Daskalakis S et al (2018) Four-PAM modulation of ambient FM backscattering for spectrally efficient low-power applications. IEEE Trans Microw Theory Tech 66(12):5909–5921

    Google Scholar 

  5. Ali A, Hamouda W (2015) Spectrum monitoring using energy ratio algorithm for OFDM-based cognitive radio networks. IEEE Trans Wirel Commun 14(4):2257–2268

    Google Scholar 

  6. Ma J, Qiu T (2018) Automatic modulation classification using cyclic correntropy spectrum in impulsive noise. IEEE Wirel Commun Lett 8(2):440–443

    Google Scholar 

  7. Zheng Q et al (2018) Improvement of generalization ability of deep CNN via implicit regularization in two-stage training process. IEEE Access 6:15844–15869

    Google Scholar 

  8. Zheng J, Lv Y (2018) Likelihood-Based automatic modulation classification in OFDM with index modulation. IEEE Trans Veh Technol 67(9):8192–8204

    Google Scholar 

  9. Wang F, Dobre Q, Chan C, Zhang J (2016) Fold-based Kolmogorov–Smirnov modulation classifier. IEEE Signal Process Lett 23(7):1003–1007

    Google Scholar 

  10. Richmond CD, Basu P (2018) Architectures for cooperative radar-communications: average vs. generalized likelihood ratio tests. In: IEEE Radar Conference (RadarConf18), Oklahoma City, USA, pp 1584–1588

  11. Moghaddam S, Habibzadeh A (2018) Cooperative spectrum sensing based on generalized likelihood ratio test for cognitive radio channels with unknown primary user’s power and colored noise. Int J Sensors Wirel Commun Control 8(3):217–227

    Google Scholar 

  12. Zheng Q et al (2020) PAC-Bayesian framework based drop-path method for 2D discriminative convolutional network pruning. Multidimension Syst Signal Process 31(3):793–827

    MathSciNet  MATH  Google Scholar 

  13. Zheng Q et al (2017) Fine-grained image classification based on the combination of artificial features and deep convolutional activation features. In: IEEE/CIC international conference on communications in China (ICCC), pp 1–6, Qingdao, China

  14. Wang D, Zhang N, Li Z, Gao F, Shen X (2017) Leveraging high order cumulants for spectrum sensing and power recognition in cognitive radio networks. IEEE Trans Wirel Commun 17(2):1298–1310

    Google Scholar 

  15. Xie L, Wan Q (2017) Cyclic feature based modulation recognition using compressive sensing. IEEE Wirel Commun Lett 6(3):402–405

    Google Scholar 

  16. Wei Y, Fang S, Wang X (2019) Automatic modulation classification of digital communication signals using SVM based on hybrid features, cyclostationary, and information entropy. Entropy 21(8):1–17

    MathSciNet  Google Scholar 

  17. Hazar M, Odabasioglu N, Ensari T, Kavurucu Y, Sayan O (2018) Performance analysis and improvement of machine learning algorithms for automatic modulation recognition over Rayleigh fading channels. Neural Comput Appl 29(9):351–360

    Google Scholar 

  18. Daldal N, Yıldırım Ö, Polat K (2019) Deep long short-term memory networks-based automatic recognition of six different digital modulation types under varying noise conditions. Neural Comput Appl 31(6):1967–1981

    Google Scholar 

  19. Zheng Q, Tian X, Jiang N, Yang M (2019) Layer-wise learning based stochastic gradient descent method for the optimization of deep convolutional neural network. J Intell Fuzzy Syst 37(4):5641–5654

    Google Scholar 

  20. Alaeddine H, Jihene M (2020) Deep network in network. Neural Process Appl. https://doi.org/10.1007/s00521-020-05008-0

  21. He Y, Mendis GJ, Wei J (2017) Real-time detection of false data injection attacks in smart grid: a deep learning-based intelligent mechanism. IEEE Trans Smart Grid 8(5):2505–2516

    Google Scholar 

  22. Ye H, Li G, Juang B (2017) Power of deep learning for channel estimation and signal detection in OFDM systems. IEEE Wirel Commun Lett 7(1):114–117

    Google Scholar 

  23. Mao B et al (2017) Routing or computing? The paradigm shift towards intelligent computer network packet transmission based on deep learning. IEEE Trans Comput 66(11):1946–1960

    MathSciNet  MATH  Google Scholar 

  24. Yuan X, Ou C, Wang Y, Yang C, Gui W (2019) A layer-wise data augmentation strategy for deep learning networks and its soft sensor application in an industrial hydrocracking process. IEEE Trans Neural Netw Learn Syst

  25. O’Shea TJ, Roy T, Clancy TC (2018) Over-the-air deep learning based radio signal classification. IEEE J Sel Top Signal Process 12(1):168–179

    Google Scholar 

  26. Zeng Y, Zhang M, Han F, Gong Y, Zhang J (2019) Spectrum analysis and convolutional neural network for automatic modulation recognition. IEEE Wirel Commun Lett 8(3):929–932

    Google Scholar 

  27. Kumar Y, Amit S, Prasanna C (2018) A learnable distortion correction module for modulation recognition. IEEE Wirel Commun Lett 8(1):77–80

    Google Scholar 

  28. Wu Y, Li X, Fang J (2018) A deep learning approach for modulation recognition via exploiting temporal correlations. In: IEEE international workshop on signal processing advances in wireless communications (SPAWC), Kalamata, Greece, pp 1–5

  29. Zhang M, Zeng Y, Han Z, Gong Y (2018) Automatic modulation recognition using deep learning architectures. In: IEEE international workshop on signal processing advances in wireless communications (SPAWC), Kalamata, Greece, pp 1–5

  30. Xie W et al (2019) Deep learning in digital modulation recognition using high order cumulants. IEEE Access 7:63760–63766

    Google Scholar 

  31. Ali A, Yang F (2017) Automatic modulation classification using deep learning based on sparse autoencoders with nonnegativity constraints. IEEE Signal Process Lett 24(11):1626–1630

    Google Scholar 

  32. Schmidt L, Santurkar S, Tsipras D, Talwar K, Madry A (2018) Adversarially robust generalization requires more data. In: Advances in neural information processing systems (NeurIPS), Montreal, Canada, pp 5014–5026

  33. Holland M, Ikeda K (2019) Better generalization with less data using robust gradient descent. In: International conference on machine learning (ICML), Long Beach, USA, pp 2761–2770

  34. Zhang X, Chen B, Liu H, Zuo L, Feng B (2016) Infinite max-margin factor analysis via data augmentation. Pattern Recogn 52:17–32

    MATH  Google Scholar 

  35. Xie L, Wang J, Wei Z, Wang M, Tian Q (2016) DisturbLabel: regularizing CNN on the loss layer. In: IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, USA, pp 4753–4762

  36. Proenca H, Neves JC, Marques T, Barra S, Moreno JC (2016) Joint head pose/soft label estimation for human recognition in-the-wild. IEEE Trans Pattern Anal Mach Intell 38(12):2444–2456

    Google Scholar 

  37. Inoue H (2018) Data augmentation by pairing samples for images classification. In: International conference on learning representations (ICLR), Vancouver, Canada, pp 313–322

  38. Perez L, Wang J (2018) The effectiveness of data augmentation in image classification using deep learning. IEEE Trans Image Process 27(3):547–554

    Google Scholar 

  39. Lemley J, Bazrafkan S, Corcoran P (2017) Smart augmentation learning an optimal data augmentation strategy. IEEE Access 5:5858–5869

    Google Scholar 

  40. Tang B, Tu Y, Zhang Z, Lin Y (2018) Digital signal modulation classification with data augmentation using generative adversarial nets in cognitive radio networks. IEEE Access 6:15713–15722

    Google Scholar 

  41. Srivastava N et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958

    MathSciNet  MATH  Google Scholar 

  42. Wan L, Zeiler M, Zhang S, Cun Y, Fergus R (2013) Regularization of neural networks using DropConnect. In: International conference on machine learning (ICML), Atlanta, Georgia, USA, pp 1058–1066

  43. Park DS et al. (2019) SpecAugment: A simple data augmentation method for automatic speech recognition. arXiv preprint, arXiv:1904.08779

  44. Cui X, Goel V, Kingsbury B (2015) Data augmentation for deep neural network acoustic modeling. IEEE/ACM Trans Audio Speech Lang Process 23(9):1469–1477

    Google Scholar 

  45. Qian Y, Hu H, Tan T (2019) Data augmentation using generative adversarial networks for robust speech recognition. Speech Commun 114:1–9

    Google Scholar 

  46. Yoo KM, Shin Y, Lee S (2019) Data augmentation for spoken language understanding via joint variational generation. In: AAAI conference on artificial intelligence (AAAI), Hawaii, USA, pp 7402–7409

  47. Sun X, He J (2020) A novel approach to generate a large scale of supervised data for short text sentiment analysis. Multimed Tools Appl 79(9):5439–5459

    Google Scholar 

  48. Hu Z, Tan B, Salakhutdinov R, Mitchell TM, Xing EP (2019) Learning data manipulation for augmentation and weighting. In: Advances in neural information processing systems (NeurIPS), Vancouver, Canada, pp 15764–15775

  49. Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980

  50. Atchadé YF, Fort G, Moulines E (2017) On perturbed proximal gradient algorithms. J Mach Learn Res 18(1):310–342

    MathSciNet  MATH  Google Scholar 

  51. Laurens VDM, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9:2579–2605

    MATH  Google Scholar 

  52. Liu T, Guan Y, Lin Y (2017) Research on modulation recognition with ensemble learning. EURASIP J Wirel Commun Netw 179(1):1–10

    Google Scholar 

  53. Zheng Q, Yang M, Tian X, Jiang N, Wang D (2020) A full stage data augmentation method in deep convolutional neural network for natural image classification. Discrete Dyn Nat Soc. https://doi.org/10.1155/2020/4706576

  54. Nápoles G et al (2017) Rough cognitive ensembles. Int J Approx Reason 85:79–96

    MathSciNet  MATH  Google Scholar 

  55. Rakotomamonjy A, Canu S (2005) Frames, reproducing kernels, regularization and learning. J Mach Learn Res 6(3):1485–1515

    MathSciNet  MATH  Google Scholar 

  56. Blossom E (2004) GNU radio: tools for exploring the radio frequency spectrum. Linux J 2004(122):4

    Google Scholar 

  57. Bloessl B et al (2013) Towards an open source IEEE 802.11p stack: a full SDR-based transceiver in GNU radio. In: IEEE vehicular networking conference, Boston, USA, pp 143–149

  58. Santurkar S, Tsipras D, Ilyas A, Madry A (2018) How does batch normalization help optimization? In: Advances in neural information processing systems, Montreal, Canada, pp 2483–2493

  59. Lin M, Chen Q, Yan S (2014) Network in network. In: International conference on learning representations (ICLR), Banff, Canada, pp 1–10

  60. Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: International conference on artificial intelligence and statistics, Sardinia, Italy, pp 249–256

  61. He K, Girshick R, Dollár P (2019) Rethinking ImageNet pre-training. In: IEEE international conference on computer vision (ICCV), Seoul, Korea, pp 4918–4927

  62. Peng S et al (2018) Modulation classification based on signal constellation diagrams and deep learning. IEEE Trans Neural Netw Learn Syst 30(3):718–727

    Google Scholar 

  63. Sang Y, Li L (2018) Application of novel architectures for modulation recognition. In: IEEE Asia Pacific conference on circuits and systems (APCCAS), Chengdu, China, pp 159–162

  64. Yang F et al (2016) A novel method for wireless communication signal modulation recognition in smart grid. J Commun 11(9):813–818

    Google Scholar 

Download references

Funding

This work was supported by National Key R&D Program of China (Grant 2018YFF01014304, 2012YQ20022407), Major Basic Research Project of Shandong Provincial Natural Science Foundation (Grant ZR2019ZD01), and Fundamental Research Founds of Shandong University (Grant 104222019).

Author information

Authors and Affiliations

  1. School of Information Science and Engineering, Shandong University, Qingdao, 266237, China

    Qinghe Zheng, Penghui Zhao, Hongjun Wang & Yang Yang

  2. Public (Innovation) Experimental Teaching Center, Shandong University, Qingdao, 266237, China

    Hongjun Wang

  3. School of Information Science and Engineering, University of Jinan, Jinan, 250022, China

    Yang Li

  4. Shandong Provincial Key Laboratory of Network Based Intelligent Computing, Jinan, 250022, China

    Yang Li

Authors
  1. Qinghe Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Penghui Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hongjun Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yang Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Hongjun Wang or Yang Yang.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Code availability

The convergent deep CNN model, test procedure, more visualized convolution kernels, and the public dataset RadioML 2016.10a in MATLAB have been open sourced on GitHub: https://github.com/a1178916307/deep-CNN-for-modulation-classification.git. The full source code and presentation will be released after the paper has been accepted.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix

Appendix

For the convenience of readers following and understanding this paper, we have annotated all variables in Table 5. In addition, the convergent deep CNN model, test procedure, more visualized convolution kernels, and the public dataset RadioML 2016.10a in MATLAB have been open sourced on GitHub: https://github.com/a1178916307/deep-CNN-for-modulation-classification.git. The full source code and presentation will be released after the paper has been accepted.

Table 5 Annotations of symbols
Full size table

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zheng, Q., Zhao, P., Li, Y. et al. Spectrum interference-based two-level data augmentation method in deep learning for automatic modulation classification. Neural Comput & Applic 33, 7723–7745 (2021). https://doi.org/10.1007/s00521-020-05514-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-020-05514-1

Keywords

Search

Navigation