Journal of the Korea Institute of Military Science and Technology (한국군사과학기술학회지)

The Korea Institute of Military Science and Technology (한국군사과학기술학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of Jamming Techniques by Using LSTM

LSTM을 이용한 재밍 기법 예측

  • Lee, Gyeong-Hoon (Department of Computer Science and Engineering, Chungnam National University) ;
  • Jo, Jeil (The 2nd Research and Development Institute, Agency for Defense Development) ;
  • Park, Cheong Hee (Department of Computer Science and Engineering, Chungnam National University)
  • 이경훈 (충남대학교 컴퓨터공학과) ;
  • 조제일 (국방과학연구소 제2기술연구본부) ;
  • 박정희 (충남대학교 컴퓨터공학과)
  • Received : 2018.11.26
  • Accepted : 2019.02.25
  • Published : 2019.04.05
Download PDF
⟨ Previous Next ⟩

Abstract

Conventional methods for selecting jamming techniques in electronic warfare are based on libraries in which a list of jamming techniques for radar signals is recorded. However, the choice of jamming techniques by the library is limited when modified signals are received. In this paper, we propose a method to predict the jamming technique for radar signals by using deep learning methods. Long short-term memory(LSTM) is a deep running method which is effective for learning the time dependent relationship in sequential data. In order to determine the optimal LSTM model structure for jamming technique prediction, we test the learning parameter values that should be selected, such as the number of LSTM layers, the number of fully-connected layers, optimization methods, the size of the mini batch, and dropout ratio. Experimental results demonstrate the competent performance of the LSTM model in predicting the jamming technique for radar signals.

Keywords

GSGGBW_2019_v22n2_278_f0001.png 이미지

Fig. 1. The basic structure of ANN

GSGGBW_2019_v22n2_278_f0002.png 이미지

Fig. 2. The basic structure of RNN

GSGGBW_2019_v22n2_278_f0003.png 이미지

Fig. 3. Types of RF

GSGGBW_2019_v22n2_278_f0004.png 이미지

Fig. 4. Types of PRI

GSGGBW_2019_v22n2_278_f0005.png 이미지

Fig. 5. The basic structure for LSTM model

GSGGBW_2019_v22n2_278_f0006.png 이미지

Fig. 6. Validation accuracy by optimazation methods

GSGGBW_2019_v22n2_278_f0007.png 이미지

Fig. 7. The validation accuracy by batch sizes

GSGGBW_2019_v22n2_278_f0008.png 이미지

Fig. 8. The validation accuracy by dropout rates

GSGGBW_2019_v22n2_278_f0009.png 이미지

Fig. 9. Model structures with 1 or 2 LSTM layers

GSGGBW_2019_v22n2_278_f0010.png 이미지

Fig. 10. The validation accuracy by LSTM layers

GSGGBW_2019_v22n2_278_f0011.png 이미지

Fig. 11. Model structure with a fully connected layer

GSGGBW_2019_v22n2_278_f0012.png 이미지

Fig. 12. The validation accuracy by FCL

GSGGBW_2019_v22n2_278_f0013.png 이미지

Fig. 13. The validation accuracy by feature sets

GSGGBW_2019_v22n2_278_f0014.png 이미지

Fig. 14. Validation accuracy by learning rate decay

Table 1. Parameters

GSGGBW_2019_v22n2_278_t0001.png 이미지

Table 2. The best accuracy by optimization methods

GSGGBW_2019_v22n2_278_t0002.png 이미지

Table 3. The best accuracy by batch sizes

GSGGBW_2019_v22n2_278_t0003.png 이미지

Table 4. The best accuracy by dropout rates

GSGGBW_2019_v22n2_278_t0004.png 이미지

Table 5. The best accuracy by LSTM layers

GSGGBW_2019_v22n2_278_t0005.png 이미지

Table 6. The best accuracy by FCL

GSGGBW_2019_v22n2_278_t0006.png 이미지

Table 7. The best accuracy by feature sets

GSGGBW_2019_v22n2_278_t0007.png 이미지

Table 8. The best ccuracy by learning rate decay

GSGGBW_2019_v22n2_278_t0008.png 이미지

Table 9. Accuracy(%) of train, validation, test data

GSGGBW_2019_v22n2_278_t0009.png 이미지

References

  1. R. N. Lothes, M. B. Szymanski, and R. G. Wiley, "Radar Vulnerability to Jamming," Artech House, 685 Canton Street, Norwood, MA, pp. 29-134, 1990.
  2. L. Jian-xun, S. Qi. and Y. Hai, "Signal Feature Analysis and Experimental Verification of Radar Deception Jamming," IEEE CIE International Conference on Radar, Vol. 1, pp. 230-233, 2011.
  3. A. Mendoza, "Classification of Radar Jammer FM Signals Using a Neural Network Approach," PhD Thesis, The University of Texas at El Paso, 2017.
  4. Y. J. Ryoo and W. W. Kim, “Recognition of PRI Modulation Types of Radar Signals Using the Autocorrelation,” The Institute of Electronics Engineers of Korea, Vol. 43, No. 3, pp. 61-68, 2006.
  5. G. P. Noone, "A Neural Approach to Automatic Pulse Repetition Interval Modulation Recognition," Information, Decision and Control, pp. 213-218, 1999.
  6. J. P. Kauppi and K. S. Martikainen, "An Efficient Set of Features for Pulse Repetition Interval Modulation Recognition," 2007 IET International Conference on Radar Systems, pp. 1-5, 2007.
  7. J. W. Han and J. H. Jin, “A Novel Method of Recognizing PRI Modulation Type of Radar Signal based on Support Vector Machine,” The Institute of Electronics and Information Engineers, Vol. 2017, No. 6, pp. 679-682, 2017.
  8. Z. Wu, Y. Zhao, Z. Yin and H. Luo, "Jamming Signals Classification Using Convolutional Neural Network," IEEE International Symposium on Signal Processing and Information Technology(ISSPIT), pp. 062-067, 2017.
  9. S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computationm, Vol. 9, No. 8, pp. 1735-1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735
  10. N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever and R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Over-Fitting,” The Journal of Machine Learning Research, Vol. 15, No. 1, pp. 1929-1958, 2014.