DOI QR코드

DOI QR Code

Experimental performance analysis on the non-negative matrix factorization-based continuous wave reverberation suppression according to hyperparameters

비음수행렬분해 기반 연속파 잔향 제거 기법의 초매개변숫값에 따른 실험적 성능 분석

  • Received : 2022.10.20
  • Accepted : 2022.12.03
  • Published : 2023.01.31

Abstract

Recently, studies on reverberation suppression using Non-negative Matrix Factorization (NMF) have been actively conducted. The NMF method uses a cost function based on the Kullback-Leibler divergence for optimization. And some constraints are added such as temporal continuity, pulse length, and energy ratio between reverberation and target. The tendency of constraints are controlled by hyperparameters. Therefore, in order to effectively suppress reverberation, hyperparameters need to be optimized. However, related studies are insufficient so far. In this paper, the reverberation suppression performance according to the three hyperparameters of the NMF was analyzed by using sea experimental data. As a result of analysis, when the value of hyperparameters for time continuity and pulse length were high, the energy ratio between the reverberation and the target showed better performance at less than 0.4, but it was confirmed that there was variability depending on the ocean environment. It is expected that the analysis results in this paper will be utilized as a useful guideline for planning precise experiments for optimizing hyperparameters of NMF in the future.

최근 비음수행렬분해 기법을 이용한 잔향 제거 연구가 활발히 이루어지고 있다. 비음수행렬분해 기법은 최적화를 위해 쿨백라이블러 발산 기반의 비용함수를 사용하며, 시간 연속성, 펄스 길이, 잔향과 표적 간 에너지 비율 등 제약사항들이 추가된다. 그리고 초매개변수를 이용하여 제약사항이 적용되는 경향을 조절한다. 따라서 효율적인 잔향 제거를 위해서는 초매개변수를 최적화해야 하지만 현재까지는 관련된 연구가 미흡한 실정이다. 본 논문에서는 실제 해상실험 데이터를 이용하여 비음수행렬분해 기반 잔향 제거 기법의 세 가지 초매개변수에 따른 잔향 제거 성능을 분석하였다. 분석결과, 시간 연속성과 펄스 길이에 대한 초매개변수는 값이 높을 경우 잔향과 표적 간의 에너지 비율은 0.4 이하에서 우수한 성능을 보였으나, 변화하는 송수신 환경에 따라서 성능의 변동성이 있음을 확인하였다. 본 논문의 분석 결과가 향후 비음수행렬분해 기반 연속파 잔향 제거 기법의 초매개변수를 최적화하기 위한 정밀한 실험을 계획하는 것에 유용한 지침표가 될 수 있을 것으로 기대한다.

Keywords

Acknowledgement

본 논문은 국방과학연구소의 응용연구 과제인 "플랫폼 간 양상태 소나기술"의 연구결과를 포함합니다.

References

  1. Y. T. Chan, Underwater acoustic data processing, NATO ASI Series, vol 616. (Springer, Dordrecht, 1989), pp. 3-24.
  2. D. A. Abraham, Underwater Acoustic Signal Processing, Modeling, Detection, and Estimation (Springer, Berlin, 2019), pp. 36-48.
  3. B. W. Choi, E. H. Bae, J. S. Kim, and K. K. Lee, "Improved prewhitening method for linear frequency modulation reverberation using dechirping transformation," J. Acoust. Soc. Am. 123, EL21-EL25 (2008). https://doi.org/10.1121/1.2838249
  4. S. Lee and J.-S. Lim, "Reverberation suppression using non-negative matrix factorization to detect low-doppler target with continuous wave active sonar," EURASIP Adv. Signal Process. 1, 1-18 (2019).
  5. G. Kim, K. Lee, and S. Lee, "Linear frequency modulated reverberation suppression using non-negative matrix factorization methods, dechirping transformation and modulo operation," IEEE Access. 8, 110720-110737 (2020). https://doi.org/10.1109/access.2020.3001865
  6. G. Kim, K. Lee, and S. Lee, "Reverberation suppression method for active sonar systems using nonnegative matrix factorization with pre-trained frequency basis matrix," IEEE Access. 8, 148060-148075 (2021). https://doi.org/10.1109/ACCESS.2021.3124509
  7. S. Lee, J.-S. Lim, and M. Jeong, "Reverberation suppression algorithm for continuous-wave active sonar system based on overlapping nonnegative matrix factorization" (in Korean), J. Acoust. Soc. Kr. 36, 273- 278 (2017).
  8. S. Lee, "Target detection method of the narrow-band continuous-wave active sonar based on basis-group beamspace-domain nonnegative matrix factorization for a reverberant environment" (in Korean), J. Acoust. Soc. Kr. 38, 290-301 (2019).
  9. D. D. Lee and H. S. Seung, "Learning the parts of objects by non-negative matrix factorization," Nature, 401, 788-791 (1999). https://doi.org/10.1038/44565
  10. Todd K. Leen, Thomas G. Dietterich and Volker Tresp, Advances in Neural Information Processing Systems 13, (MIT Press, England, 2001), pp. 556-562.
  11. T. Virtanen, "Monaural sound source separation by nonnegative matrix factorization with temporal continuity and sparseness criteria," IEEE Trans. Audio, Speech, Language Process. 15, 1066-1074 (2007). https://doi.org/10.1109/TASL.2006.885253