DOI QR코드

DOI QR Code

Classification of Radio Signals Using Wavelet Transform Based CNN

웨이블릿 변환 기반 CNN을 활용한 무선 신호 분류

  • Song, Minsuk (Department of Military Digital Convergence, Ajou University) ;
  • Lim, Jaesung (Department of Military Digital Convergence, Ajou University) ;
  • Lee, Minwoo (Department of Military Digital Convergence, Ajou University)
  • Received : 2022.06.17
  • Accepted : 2022.07.08
  • Published : 2022.08.31

Abstract

As the number of signal sources with low detectability by using various modulation techniques increases, research to classify signal modulation methods is steadily progressing. Recently, a Convolutional Neural Network (CNN) deep learning technique using FFT as a preprocessing process has been proposed to improve the performance of received signal classification in signal interference or noise environments. However, due to the characteristics of the FFT in which the window is fixed, it is not possible to accurately classify the change over time of the detection signal. Therefore, in this paper, we propose a CNN model that has high resolution in the time domain and frequency domain and uses wavelet transform as a preprocessing process that can express various types of signals simultaneously in time and frequency domains. It has been demonstrated that the proposed wavelet transform method through simulation shows superior performance regardless of the SNR change in terms of accuracy and learning speed compared to the FFT transform method, and shows a greater difference, especially when the SNR is low.

다양한 변조 기법을 사용하여 저피탐 능력을 갖춘 신호원들이 증가하면서, 신호의 변조 방식을 분류하는 연구가 꾸준히 진행되고 있다. 최근 신호 간섭이나 잡음 환경에서 수신 신호 분류의 성능 개선을 위하여 전처리 과정으로 FFT를 이용하는 CNN(Convolutional Neural Network) 딥러닝 기법이 제안되었다. 하지만 윈도우가 고정되는 FFT의 특성상 탐지 신호의 시간에 따른 변화를 정확히 분류해내지 못한다. 따라서 본 논문에서는 시간 영역과 주파수 영역에서 높은 해상도를 가지고 또한 다양한 유형의 신호를 시간 및 주파수 영역에서 동시에 표현할 수 있는 웨이블릿 변환(wavelet transform)을 전처리 과정으로 사용하는 CNN 모델을 제안한다. 시뮬레이션을 통해 제안하는 웨이블릿 변환 방식이 FFT 변환 방식에 비해 정확도와 학습 속도 측면에서 SNR 변화에 무관하게 우수한 성능을 보이고, 특히 낮은 SNR일 때 더욱 큰 차이를 보임을 입증하였다.

Keywords

Acknowledgement

This work was supported by the Future Combat System Network Technology Research Center Program of Defense Acquisition Program Administration and Agency for Defense Development under Grant UD190033ED

References

  1. J. P. Stephens, "Advances in signal processing technology for electronic warfare," IEEE Aerospace and Electronic Systems Magazine, vol. 11, no. 11, pp. 31-38, Nov. 1996. https://doi.org/10.1109/62.544024
  2. USA Joint Chief of Staffs, "Joint Vision 2010," US Gov. Printing Office, Washington DC, May. 1996.
  3. P. E. Pace, "Detecting and Classifying Low Probability of Intercept Radar," MA: Artech House, USA, 2009.
  4. X. Li, F. Dong, S. Zhang, and W. Guo, "A Survey on Deep Learning Techniques in Wireless Signal Recognition," Special Physical-layer Wireless Communications, vol. 2019, Article no. 5629572, Feb. 2019.
  5. T. J. O'Shea and N. West, "Radio machine learning dataset generation with GNU radio," in Proceedings of the 6th GNU Radio Conference, Boulder: CO, USA, vol. 1, no. 1, 2016.
  6. T. J. O'Shea, J. Corgan, and T. C. Clancy, "Convolutional radio modulation recognition networks," in Proceedings of Engineering Applications of Neural Networks, Aberdeen, U.K., pp. 213-226, 2016.
  7. T. J. O'Shea, T. Roy, and T. C. Clancy, "Over-the-Air Deep Learning Based Radio Signal Classification," IEEE Journal of Selected Topics in Signal Processing, vol. 12, no. 1, pp. 168-179, Feb. 2018. https://doi.org/10.1109/JSTSP.2018.2797022
  8. T. Xu and I. Darwazeh, "Deep Learning for Over-the-Air Non-Orthogonal Signal Classification," in Proceedings of 2020 IEEE 91st Vehicular Technology Conference, Antwerp, Belgium, pp. 1-5, 2020.
  9. X. Liu, D. Yang, and A. El Gamal, "Deep neural network architectures for modulation classification," in Proceedings of 2017 51st Asilomar Conference on Signals, Systems and Computers, Pacific Grove: CA, USA, pp. 915-919, 2017.
  10. S. A. A. Karim, M. H. Kamarudin, B. A. Karim, M. K. Hasan, and J. Sulaiman, "Wavelet Transform and Fast Fourier Transform for signal compression: A comparative study," in Proceedings of 2011 International Conference on Electronic Devices, Systems and Applications, Kuala Lumpur, Malaysia, pp. 280-285, 2011.
  11. M. Akin, "Comparison of wavelet transform and FFT methods in the analysis of EEG signals," Journal of Medical Systems, vol. 26, no. 3, pp. 241-247, Jun. 2002. https://doi.org/10.1023/A:1015075101937