한국음향학회지 (The Journal of the Acoustical Society of Korea)

  • 제39권6호
  • /
  • Pages.592-599
  • /
  • 2020
  • /
  • 1225-4428(pISSN)
  • /
  • 2287-3775(eISSN)
한국음향학회 (The Acoustical Society of Korea)
권호 표지
DOI QR코드

DOI QR Code

합성곱 순환 신경망 구조를 이용한 지진 이벤트 분류 기법

Earthquake events classification using convolutional recurrent neural network

  • 구본화 (고려대학교 전기전자전파 공학부) ;
  • 김관태 (고려대학교 전기전자전파 공학부) ;
  • 장수 (고려대학교 전기전자전파 공학부) ;
  • 고한석 (고려대학교 전기전자전파 공학부)
  • 투고 : 2020.07.31
  • 심사 : 2020.10.19
  • 발행 : 2020.11.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문은 다양한 지진 이벤트 분류를 위해 지진 데이터의 정적인 특성과 동적인 특성을 동시에 반영할 수 있는 합성곱 순환 신경망(Convolutional Recurrent Neural Net, CRNN) 구조를 제안한다. 중규모 지진뿐만 아니라 미소 지진, 인공 지진을 포함한 지진 이벤트 분류 문제를 해결하려면 효과적인 특징 추출 및 분류 방법이 필요하다. 본 논문에서는 먼저 주의 기반 합성곱 레이어를 통해 지진 데이터의 정적 특성을 추출 하게 된다. 추출된 특징은 다중 입력 단일 출력 장단기메모리(Long Short-Term Memory, LSTM) 네트워크 구조에 순차적으로 입력되어 다양한 지진 이벤트 분류를 위한 동적 특성을 추출하게 되며 완전 연결 레이어와 소프트맥스 함수를 통해 지진 이벤트 분류를 수행한다. 국내외 지진을 이용한 모의 실험 결과 제안된 모델은 다양한 지진 이벤트 분류에 효과적인 모습을 보여 주었다.

This paper proposes a Convolutional Recurrent Neural Net (CRNN) structure that can simultaneously reflect both static and dynamic characteristics of seismic waveforms for various earthquake events classification. Addressing various earthquake events, including not only micro-earthquakes and artificial-earthquakes but also macro-earthquakes, requires both effective feature extraction and a classifier that can discriminate seismic waveform under noisy environment. First, we extract the static characteristics of seismic waveform through an attention-based convolution layer. Then, the extracted feature-map is sequentially injected as input to a multi-input single-output Long Short-Term Memory (LSTM) network structure to extract the dynamic characteristic for various seismic event classifications. Subsequently, we perform earthquake events classification through two fully connected layers and softmax function. Representative experimental results using domestic and foreign earthquake database show that the proposed model provides an effective structure for various earthquake events classification.

키워드

참고문헌

  1. H. I. Fawaz, G. Forestier, J. Weber, L. Idoumghar, and P.-A. Muller, "Deep learning for time series classification: a review," arXiv: 1809.04356 (2018).
  2. Z. Cui, W. Chen, and Y. Chen, "Multi-scale convolutional neural networks for time series classification," arXiv:1603.06995 (2016).
  3. J. Lee, J. Park, K. L. Kim, and J. Nam, "SampleCNN : End-to-end deep convolutional neural networks using very small filter for music classifications," Applied Science, 8, 150 (2018). https://doi.org/10.3390/app8010150
  4. X. Zeng, D. Zhou, and X. Zeng, "HeartID: A multiresolution convolutional neural network for ECGbased biometric human identification in smart health applications," IEEE Access, 5, 11805-11816 (2017). https://doi.org/10.1109/ACCESS.2017.2707460
  5. K. Choi, G. Fazekas, M. Sandler, and K. Cho, "Convolutional recurrent neural networks for music classification," arXiv:1609.04243v3 (2016).
  6. B. Ku, J. Min, J.-K. Ahn, J. Lee, and H. Ko, "Earthquake event classification using multitasking deep learning," IEEE Geoscience and Remote Sensing Letters, early access, 1-5 (2020).
  7. M. Withers, R. Aster, C. Young, J. Beiriger, M. Harris, S. Moore, and J. Trujillo, "A comparison of select trigger algorithms for automated global seismic phase and event detection," Bull. Seismol. Soc. Am. 88, 95-106, (1998).
  8. S. J. Gibbons and F. Ringdal, "The detection of low magnitude seismic events using array-based waveform correlation," Geophys. J. Int. 165, 149-166 (2006). https://doi.org/10.1111/j.1365-246X.2006.02865.x
  9. J. Skoumal, M. R. Brudzinski, B. S. Currie, and J. Levy, "Optimizing multi-station earthquake template matching through re-examination of the Youngstown, Ohio, sequence," Earth and Planet Science Letters, 405, 274-280 (2014). https://doi.org/10.1016/j.epsl.2014.08.033
  10. C. E. Yoon, O. O'Reilly, P. J. Bergen, and G. C. Beroza, "Earthquake detection through computationally efficient similarity search," Science Advances, 1, e1501057 (2015). https://doi.org/10.1126/sciadv.1501057
  11. T. Perol, M. Gharbi, and M. Denolle, "Convolutional neural network for earthquake detection and location," Science Advances, 4, e1700578 (2018). https://doi.org/10.1126/sciadv.1700578
  12. S. M. Mousavi, W. Zhu, Y. Sheng, and G. C. Beroza, "CRED: A deep residual network of convolutional and recurrent units for earthquake signal detection," arXiv:1810.01965 (2018).
  13. A. Mignan and M. Broccardo, "Neural network applications in earthquake prediction (1994-2019): Metaanalytic insight on their limitations," arXiv:1910.011 78 [cs.NE] (2019).
  14. J. Hu, L. Shen, S. Albanie, G. Sun, and E. Wuf, "Squeeze-and-excitation networks," arXiv:1709.01507 (2017).
  15. S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, 9, 1735-1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735
  16. S. Ioffe and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," arXiv:1502.03167 (2015).
  17. R. E. Woods and R. C. Gonzalez, Digital Image Processing (Pearson, New York, 2018), pp. 129-130.
  18. N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: A simple way to prevent neural networks from overfitting," J. Machine Learning Research, 15, 1929-1958 (2014).
  19. NECIS, http://necis.kma.go.kr//, (Last viewed March 31, 2020).
  20. S. M. Mousavi, Y. Sheng, W. Zhu, and G. C. Beroza, "STanford EArthquake Dataset (STEAD): A global data set of seismic signals for AI," IEEE Access, 7, 179464-179476 (2019). https://doi.org/10.1109/ACCESS.2019.2947848