한국음향학회지 (The Journal of the Acoustical Society of Korea)

  • 제43권2호
  • /
  • Pages.234-242
  • /
  • 2024
  • /
  • 1225-4428(pISSN)
  • /
  • 2287-3775(eISSN)
한국음향학회 (The Acoustical Society of Korea)
권호 표지
DOI QR코드

DOI QR Code

영상 패치 기반 그래프 신경망을 이용한 수동소나 신호분류

Passive sonar signal classification using graph neural network based on image patch

  • 고건혁 (제주대학교 해양시스템공학과) ;
  • 이기배 (제주대학교 해양시스템공학과) ;
  • 이종현 (제주대학교 해양시스템공학과)
  • 투고 : 2024.01.22
  • 심사 : 2024.03.11
  • 발행 : 2024.03.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 그래프 신경망을 이용한 수동소나 신호 분류 알고리즘을 제안한다. 제안하는 알고리즘은 스펙트로그램을 영상 패치로 분할하고, 인접 거리의 영상 패치 간 연결을 통해 그래프를 표현한다. 이후, 표현된 그래프를 이용하여 그래프 합성곱 신경망을 학습하고 신호를 분류한다. 공개된 수중 음향 데이터를 이용한 실험에서 제안된 알고리즘은 스펙트로그램의 선 주파수 특징을 그래프 형태로 표현하며, 92.50 %의 우수한 분류 정확도를 갖는다. 이러한 결과는 기존의 합성곱 신경망과 비교하여 8.15 %의 높은 분류 정확도를 갖는다.

We propose a passive sonar signal classification algorithm using Graph Neural Network (GNN). The proposed algorithm segments spectrograms into image patches and represents graphs through connections between adjacent image patches. Subsequently, Graph Convolutional Network (GCN) is trained using the represented graphs to classify signals. In experiments with publicly available underwater acoustic data, the proposed algorithm represents the line frequency features of spectrograms in graph form, achieving an impressive classification accuracy of 92.50 %. This result demonstrates a 8.15 % higher classification accuracy compared to conventional Convolutional Neural Network (CNN).

키워드

과제정보

이 논문은 2024학년도 제주대학교 교원성과지원사업에 의하여 연구되었음.

참고문헌

  1. H. J. Lee, I. S. Seo, and K. S. Bae, "Separation of passive sonar target signals using frequency domain independent component analysis" (in Korean), J. Acoust. Soc. Kr. 35, 110-117 (2016). 
  2. R. J. Urick, Principles of Underwater Sound (McGraw-Hill, New York, 1993), pp. 302-310. 
  3. J. K. Ahn, H. D. Cho, D. Shin, T. Kwon, and G. T. Kim, "LOFAR/DEMON grams compression method for passive sonar" (in Korean), J. Acoust. Soc. Kr. 39, 28-46 (2020). 
  4. S. E. Lee, S. B. Hwang, and D. Y. Noh, "A study on the algorithm for underwater target automatic classification using the passive sonar" (in Korean), J. KIMS Technol. 3, 76-84 (2000). 
  5. H. S. Kim, "Intelligent feature extraction and scoring algorithm for classification of passive sonar target" (in Korean), J. Korean Inst. Intell. Syst. 19, 629-634 (2009). 
  6. J. d. C. V. Fernandes, N. N. de Moura Junior, and J.M. de Seixas, "Deep learning models for passive sonar signal classification of military data," Remote Sens. 14, article no. 2648 (2022). 
  7. C. Satheesh, S. Kamel, A. Mujeeb, and M. H. Supriya, "Passive sonar target classification using deep generative β-VAE," IEEE Signal Process Lett, 28, 808-812 (2021). 
  8. V. S. Doan, T. Huynh-The, and D. S. Kim, "Underwater acoustic target classification based on dense convolutional neural network," IEEE Geosci. Remote Sens. Lett. 19, 1-5 (2022). 
  9. S. Kim, S. K. Jung, D. Kang, M. Kim, and S. Chon, "Application of the artificial intelligence for automatic detection of shipping noise in shallow-water" (in Korean). J. Acoust. Soc. Kr. 39, 279-285 (2020). 
  10. K. B. Lee, G. H. Ko, and C. H. Lee, "Passive sonar signal classification using attention based gated recurrent unit" (in Korean). J. Acoust. Soc. Kr. 42, 345-356 (2023). 
  11. S. Kamal, C. S. Chandran, and M. H. Supriya, "Passive sonar automated target classifier for shallow waters using end-to-end learnable deep convolutional LSTMs," Eng. Sci. Technol. an Int. J. 24, 860-871 (2021). 
  12. F. Liu, T. Shen, Z. Luo, D. Zhao, and S. Guo, "Underwater target recognition using convolutional recurrent neural networks with 3-D Mel-spectrogram and data augmentation," Appl. Acoust. 178, article no. 107989 (2021). 
  13. P. H. C. Avelar, A. R. Tavaras, T. L. T. da Silveira, C. R. Jung, and L. C. Lamb, "Superpixel image classification with graph attention networks," Proc. 33rd SIBGRAPI, 203-209 (2020). 
  14. P. Sellars, A. I. Aviles-Rivero, and C. B. Schonlieb, "Superpixel contracted graph-based learning for hyperspectral image classification," IEEE Trans Geosci Remote. 58, 4180-4193 (2020). 
  15. C. Aironi, S. Cornell, E. Principi, and S. Squartini, "Graph-based representation of audio signals for sound event classification," Proc. 29th EUSIPCO, 566-570 (2021). 
  16. Y. C. Jung, B. U. Kim, S. K. An, W. J. Seong, and K. H. Lee, "An algorithm for submarine passive sonar simulator" (in Korean), J. Acoust. Soc. Kr. 32, 472-483 (2013). 
  17. M. Deaett, "Signature modeling for acoustic trainer synthesis," IEEE J. Ocean. Eng. 12, 143-147 (1987). 
  18. S. H. Kang, "A study on the Lloyd's mirror effect on the underwater radiated noise for the underwater vehicle" (in Korean), J. Acoust. Soc. Kr. 40, 314-319 (2021). 
  19. L. E. Kinsler, A. R. Frey, A. B. Coppens, and J. V. Sanders, Fundamentals of Acoustics (John Wiley & Sons, New Jersey, 1999), pp. 446-448. 
  20. M. Zhang, Z. Cui, M. Neumann, and Y. Chen, "An end-to-end deep learning architecture for graph classification," Proc. 32nd AAAI. Conf. Artificial Int. 4438- 4445 (2018). 
  21. T. N. Kipf and M. Welling, "Semi-supervised classification with graph convolutional networks," arXiv preprint, (2016). 
  22. N. Shervashidze, P. Schweitzer, E. J. Van Leeuwen, K. Mehlhorn, and K. M. Borgwardt, "Weisfeiler-lehman graph kernels," J. Mach. Learn. Res. 12, 2539-2561 (2011). 
  23. Z. Ying, J. You, C. Morris, X. Ren, W. Hamilton, and J. Leskovec, "Hierarchical graph representation learning with differentiable pooling," 32nd Adv. Neural Inf. Process. Syst. 1-11 (2018). 
  24. D. S. Domingues, S. T. Guizarro, A. C. Lopez, and A. P. Gimenez, "ShipsEar: An underwater vessel noise database," Appl. Acoust. 113, 64-69 (2016).