선박소음의 자동 식별을 위한 원샷 학습기법

김두영^*

해군소령/해군사관학교 인공지능학과 부교수

Use of One-shot Learning for Automatic Target Recognition of Surface Ship Noise

Dooyoung Kim^*

LCDR, ROK Navy/Associate Professor, Dept. of Artificial Intelligence, Republic of Korea Naval Academy

Correspondence to: ^*Dooyoung Kim Dept. of Artificial Intelligence, Republic of Korea Naval Academy Jungwon-ro, Jinhae-gu, Changwon-si, Gyungsangnam-do, 51704, Republic of Korea Tel: +82-55-907-5246 E-mail: dykim07@navy.ac.kr

초록

본 논문은 수중에 방사되는 선박 소음을 자동으로 식별하기 위한 원-샷 학습기법을 제시한다. 제안한 학습기법은 기존의 지도학습 기반의 딥 러닝 기법이 가지는 학습데이터의 의존성을 극복하여, 단 하나의 신호 표본만으로 동일 선박을 식별할 수 있는 모델을 공개 데이터 기반의 실험을 통해 성능을 검증한 결과 후보군이 다섯 척인 상황에서 72.5 %의 정확도로 대상 선박의 선명을 예측함을 확인하였다.

Abstract

This paper presents a one-shot learning technique for automatically identifying ship noise emitted underwater. The proposed learning technique overcomes the dependence of the learning data of the existing supervised learning-based deep learning technique and a model that can identify the same ship with only a single signal sample. As a result of verifying the performance through open data-based experiments, it was confirmed that the clarity of the target ship was predicted with an accuracy of 72.5% in the situation of five candidates.

Keywords:

Automatic Target Recognition, Meta Learning, One-shot Learning, Ship Noise

키워드:

자동 표적 인지, 메타 학습, 원샷 학습, 선박 소음

Acknowledgments

이 논문은 2023년 해군사관학교 해양연구소 학술연구과제 연구비 지원으로 수행된 연구임.

References

Xu Xiao, Wenbo Wang, Qunyan Ren, Peter Gerstoft, and Li Ma, “Underwater Acoustic Target Recognition Using Attention-based Deep Neural Network,” J. Acoust. Soc. Am. Express Letters 1, 106001 (2021). [https://doi.org/10.1121/10.0006299]
Kyung-Min Park, and Dooyoung Kim. “Preprocessing Performance of Convolutional Neural Networks According to Characteristic of Underwater Targets,” (in Korean), J. Acoust. Soc. Kr, Vol. 41, pp. 629-636 (2022).
B. Friedlander, “Accuracy of Source Localization Using Multipath Delays,” IEEE Trans. Aerospace and Electronic Systems, Vol. 24, pp. 346-359 (1988). [https://doi.org/10.1109/7.7176]
M. Johnson, L. Freitag, and M. Stojanovic, “Improved Doppler Tracking and Correction for Underwater Acoustic communications,” Proc. IEEE ICASSP. 1, pp. 575-578 (1997).
N. Owsley and G. Swope, “Time Delay Estimation in a Sensor Array,” IEEE Trans. ASSP. Vol. 29, pp. 519-523 (1981). [https://doi.org/10.1109/TASSP.1981.1163554]
W. Zhang, Y. Wu, D. Wang, Y. Wang, Y. Wang, and L. Zhang, “Underwater Target Feature Extraction and Classification Based on Gammatone Filter and Machine Learning,” Proc. ICWAPR, pp. 42-47 (2018). [https://doi.org/10.1109/ICWAPR.2018.8521356]
X. Yin, X. Sun, P. Liu, L. Wang, and R. Tang “Underwater Acoustic Target Classification Based on LOFAR Spectrum and Convolutional Neural Network,” Proc. 2nd Int. Conf. AIAM, pp. 59-63 (2020). [https://doi.org/10.1145/3421766.3421890]
H. Yang, J. Li, S. Shen, and G. Xu, “A Deep Convolutional Neural Network Inspired by Auditory Perception for Underwater Acoustic Target Recognition,” Sensors, Vol. 19, 1104 (2019). [https://doi.org/10.3390/s19051104]
Z. Wei, Y. Ju, and M. Song, “A Method of Underwater Acoustic Signal Classification Based on Deep Neural Network,” Proc. 5th ICISCE, IEEE Computer Society, pp. 46-50 (2018). [https://doi.org/10.1109/ICISCE.2018.00019]
Yang, S. et al. “A Lightweight Network Model Based on an Attention Mechanism for Ship-radiated Noise Classification,” Journal of Marine Science and Engineering, Vol. 11, No. 2, 432. (2023). [https://doi.org/10.3390/jmse11020432]
D. Santos-Dominquez, S. Torres-Guijarro, A. CardenalLopez, and A. Pena-Gimenez, “ShipsEar: An Underwater Vessel Noise Database,” Appl. Acoust. Vol. 113, pp. 64-69 (2016). [https://doi.org/10.1016/j.apacoust.2016.06.008]
M. Irfan, Z. Jiangbin, S. Ali, M. Iqbal, Z. Masood, and U. Hamid, “DeepShip: An Underwater Acoustic Benchmark Dataset and a Separable Convolution Based Autoencoder for Classification,” Expert Syst. Appl. Vol. 183, 115270 (2021). [https://doi.org/10.1016/j.eswa.2021.115270]
Bengio, Yoshua, Ian Goodfellow, and Aaron Courville. Deep learning. Vol. 1. Cambridge, MA, USA: MIT Press, 2017.
Fei-Fei, L., Fergus, R., Perona, P., "One-shot Learning of Object Categories," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28, No. 4, pp. 594–611 (2006). [https://doi.org/10.1109/TPAMI.2006.79]
Koch, G. et al, “Siamese Neural Networks for One-shot Image Recognition," In: ICML Deep Learning Workshop, Vol. 2 (2015).
Hospedales, T., Antoniou, A., Micaelli, P., and Storkey, A., “Meta-learning in Neural Networks: A Survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, No. 9, pp. 5149-5169, (2021). [https://doi.org/10.1109/TPAMI.2021.3079209]
Schörkhuber, C. and Klapuri, A, "Constant-q Transform Toolbox for Music Processing," Proc. 7th Sound and Music Computing Conf. (2010).
Brown, J.C, “Calculation of a Constant q Spectral Transform,” The Journal of the Acoustical Society of America, Vol. 89, No. 1, pp. 425–434 (1991). [https://doi.org/10.1121/1.400476]
B. McFee, C. Raffel, D. Liang, D. Ellis, M. Mcvicar, E. Battenberg, and O. Nieto, “Librosa: Audio and Music Signal Analysis in Python,” Proc. 14th Python Sci. Conf. pp. 18-24 (2015). [https://doi.org/10.25080/Majora-7b98e3ed-003]