The Journal of the Acoustical Society of Korea (한국음향학회지)

The Acoustical Society of Korea (한국음향학회)
권호 표지
DOI QR코드

DOI QR Code

Classification of bearded seals signal based on convolutional neural network

Convolutional neural network 기법을 이용한 턱수염물범 신호 판별

  • 김지섭 (한양대학교 해양융합과학과) ;
  • 윤영글 (한양대학교 해양융합과학과) ;
  • 한동균 (한국해양과학기술원 극지연구소) ;
  • 나형술 (한국해양과학기술원 극지연구소) ;
  • 최지웅 (한양대학교ERICA 해양융합공학과)
  • Received : 2022.01.18
  • Accepted : 2022.03.04
  • Published : 2022.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Several studies using Convolutional Neural Network (CNN) have been conducted to detect and classify the sounds of marine mammals in underwater acoustic data collected through passive acoustic monitoring. In this study, the possibility of automatic classification of bearded seal sounds was confirmed using a CNN model based on the underwater acoustic spectrogram images collected from August 2017 to August 2018 in East Siberian Sea. When only the clear seal sound was used as training dataset, overfitting due to memorization was occurred. By evaluating the entire training data by replacing some training data with data containing noise, it was confirmed that overfitting was prevented as the model was generalized more than before with accuracy (0.9743), precision (0.9783), recall (0.9520). As a result, the performance of the classification model for bearded seals signal has improved when the noise was included in the training data.

수동 음향 관측을 통해 수집된 방대한 양의 데이터에서 해양포유류의 소리를 탐지하고 식별하기 위해 합성곱 신경망(Convolutional Neural Network, CNN)을 활용한 연구가 많이 수행되고 있다. 본 연구는 2017년 8월부터 2018년 8월까지 동시베리아 해에서 수집된 수중음향 스펙트럼 이미지를 기반으로 CNN을 활용하여 턱수염물범 소리의 분류 자동화 가능성을 확인해 보았다. 학습 데이터로서 다른 소음이 거의 포함되지 않은 뚜렷한 턱수염물범 소리를 사용하였을 때, 암기로 인한 과적합이 발생하였다. 일부 데이터를 소음이 포함된 데이터로 교체하여 학습시켜 수집된 전체 데이터로 평가한 결과 정확도(0.9743), 정밀도(0.9783), 재현율(0.9520)으로 모델이 이전보다 일반화되어 과적합이 방지되는 것을 확인하였다. 본 연구를 통해 물범신호 분류는 학습 데이터에 소음이 포함되었을 때 성능이 증가하는 것으로 나타났다.

Keywords

Acknowledgement

이 논문은 2021년도 정부(산업통상자원부)의 재원으로 한국에너지기술평가원의 지원(20203030020080, 해상풍력 단지 해양공간 환경 영향 분석 및 데이터베이스 구축)과 2022년도 정부(해양수산부)의 재원으로 해양수산과학기술진흥원의 지원(1525011760, 북극해 온난화-해양생태계 변화 감시 및 미래전망 연구)을 받아 수행된 연구임.

References

  1. S. Lee, M. Kim, and Y. Jeong, "A study on the waveform-based end-to-end deep convolutional neural network for weakly supervised sound event detection" (in Korean), J. Acoust. Soc. Kr. 39, 24-31 (2020).
  2. H. Yang, K. Lee, Y. Choo, and K. Kim, "Underwater Acoustic Research Trends with Machine Learning General Background," J. Ocean Eng. Technol. 34, 147-154 (2020). https://doi.org/10.26748/ksoe.2020.015
  3. Y. Wang and H. Peng, "Underwater acoustic source localization using generalized regression neural network," J. Acoust. Soc. Am. 143, 2321-2331 (2018). https://doi.org/10.1121/1.5032311
  4. C. Frederick, S. Villar, and Z. H. Michalopoulou, "Seabed classification using physics-based modeling and machine learning," J. Acoust. Soc. Am. 148, 859-872 (2020). https://doi.org/10.1121/10.0001728
  5. S. Kim, S.-K. Jung, D. Kang, M. Kim, and S. Cho, "Application of the artificial intelligence for automatic detection of shipping noise in shallow-water" (in Korean), J. Acoust. Soc. Kr. 39, 279-285 (2020).
  6. S. Liu, M. Liu, M. Wang, T. Ma, and X. Qing, "Classification of cetacean whistles based on convolutional neural network," Proc. IEEE 10th ICWCSP. 1-5 (2018).
  7. W. Luo, W. Yang, and Y. Zhang, "Convolutional neural network for detecting odontocete echolocation clicks," J. Acoust. Soc. Am. 145, EL7-12 (2019). https://doi.org/10.1121/1.5085647
  8. D. Wang, L. Zhang, Z. Lu, and K. Xu, "Large-scale whale call classification using deep convolutional neural network architectures," Proc. IEEE ICSPCC. 1-5 (2018).
  9. Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel, "Backpropagation applied to handwritten zip code recognition," Neural Computation, 1, 541-551 (1989). https://doi.org/10.1162/neco.1989.1.4.541
  10. S. Behnke, Hierarchical Neural Networks for Image Interpretation (Springer, New York, 2003), pp. 44-46.
  11. A. Maccagno, A. Mastropietro, U. Mazziotta, M. Scarpiniti, Y.-C. Lee, and A. Uncini, "A CNN approach for audio classification in construction sites," in Handbook of Progresses in Artificial Intelligence and Neural Systems, edited by A. Esposito, M. Faundez-Zanuy, F. C. Morabito, and E. Pasero (Springer, Singapore, 2021).
  12. T. Lu, B. Han, and F. Yu, "Detection and classification of marine mammal sounds using AlexNet with transfer learning," Ecological Informatics, 62, 101277 (2021). https://doi.org/10.1016/j.ecoinf.2021.101277
  13. Y. Chen, W. Wang, Y. Liang, D. Zhou, C. Dong, and J. Li, "Real-time detection and classification for targeted marine mammals," Proc. 2021 OES China Ocean Acoustics, 1027-1031 (2021).
  14. S. M. Van Parijs, C. W. Clark, R. S. Sousa-Lima, S. E. Parks, S. Rankin, D. Risch, and I. C. Van Opzeeland, "Management and research applications of real-time and archival passive acoustic sensors over varying temporal and spatial scales," Marine Ecology Progress Series, 395, 21-36 (2009). https://doi.org/10.3354/meps08123
  15. M. Thomas, B. Martin, K. Kowarski, B. Gaudet, and S. Matwin, "An end-to-end approach for true detection of low frequency marine mammal vocalizations," J. Acoust. Soc. Am. 146, 2959 (2019).
  16. M. Thomas, B. Martin, K. Kowarski, B. Gaudet, and S. Matwin, "Marine mammal species classification using convolutional neural networks and a novel acoustic representation," Proc. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 290-305 (2019).
  17. C. Li, R.V. Sanchez, G. Zutita, M. Cerrada, D. Cabrera, and R. E. Vasquez, "Multimodal deep support vector classification with homologous features and its application to gearbox fault diagnosis," Neurocomputing, 168, 119-127 (2015). https://doi.org/10.1016/j.neucom.2015.06.008
  18. A. Krizhevsky, I. Sutskever, and G. E.Hinton, "Imagenet classification with deep convolutional neural networks," Proc. Advances in neural information processing systems, 25, 1097-1105 (2012).
  19. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, 86, 2278-2324 (1998). https://doi.org/10.1109/5.726791
  20. G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov, "Improving neural networks by preventing co-adaptation of feature detectors," arXiv preprint arXiv:1207.0580 (2012).
  21. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," Proc. IEEE CVPR. 770-778 (2016).
  22. A. Krizhevsky, I. Sutskever, and G. Hinton, "ImageNet classification with deep convolutional neural networks," Proc. Advances in Neural Information Processing Systems, 1097-1105 (2012).
  23. D.-G. Han, J. Joo, W. Son, K. H. Cho, J. W. Choi, E. J. Yang, J.-H. Kim, S.-H. Kang, and H. S. La, "Effects of geophony and anthrophony on the underwater acoustic environment in the East Siberian Sea, arctic ocean," Geophysical Research Letters, 48, e2021GL093097 (2021).
  24. D. Risch, C. W. Clark, P. J. Corkeron, K. M. Elepfandt, K. M. Kovacs, C. Lydersen, I. Stirling, and S. M. van Parijs, "Vocalizations of male bearded seals, Erignathus barbatus: Classification and geographical variation," Animal Behavior, 73, 747-762 (2007). https://doi.org/10.1016/j.anbehav.2006.06.012
  25. I. Charrier, N. Mathevon, and T. Aubin, "Bearded seal males perceive geographic variation in their trills," Behav. Ecol. Sociobiol. 67, 1679-1689 (2013). https://doi.org/10.1007/s00265-013-1578-6
  26. G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov, "Improving neural networks by preventing co-adaptation of feature detectors," arXiv Tech. Rep., 2012.
  27. J. Sietsma and R. Dow "Creating artificial neural networks that generalize," Neural Networks, 4, 67-79 (1991). https://doi.org/10.1016/0893-6080(91)90033-2
  28. M. Jimbo, D. Mizuguchi, H. Shirakawa, K. Tsujii, A. Fujiwara, K. Miyashita, and Y. Mitani, "Seasonal variations in the call presence of bearded seals in relation to sea ice in the southern Chukchi Sea," Polar. Biol. 42, 1953-1958 (2019). https://doi.org/10.1007/s00300-019-02569-2