Journal of Ocean Engineering and Technology (한국해양공학회지)

Korean Society of Ocean Engineers (한국해양공학회)
권호 표지
DOI QR코드

DOI QR Code

Classification of Transient Signals in Ocean Background Noise Using Bayesian Classifier

베이즈 분류기를 이용한 수중 배경소음하의 과도신호 분류

  • Kim, Ju-Ho (Department of Ocean System Engineering, Jeju National University) ;
  • Bok, Tae-Hoon (Department of Ocean System Engineering, Jeju National University) ;
  • Paeng, Dong-Guk (Department of Ocean System Engineering, Jeju National University) ;
  • Bae, Jin-Ho (Department of Ocean System Engineering, Jeju National University) ;
  • Lee, Chong-Hyun (Department of Ocean System Engineering, Jeju National University) ;
  • Kim, Seong-Il (Agency for Defense Development)
  • 김주호 (제주대학교 해양시스템공학과) ;
  • 복태훈 (제주대학교 해양시스템공학과) ;
  • 팽동국 (제주대학교 해양시스템공학과) ;
  • 배진호 (제주대학교 해양시스템공학과) ;
  • 이종현 (제주대학교 해양시스템공학과) ;
  • 김성일 (국방과학연구소)
  • Received : 2012.07.20
  • Accepted : 2012.08.20
  • Published : 2012.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, a Bayesian classifier based on PCA (principle component analysis) is proposed to classify underwater transient signals using $16^{th}$ order LPC (linear predictive coding) coefficients as feature vector. The proposed classifier is composed of two steps. The mechanical signals were separated from biological signals in the first step, and then each type of the mechanical signal was recognized in the second step. Three biological transient signals and two mechanical signals were used to conduct experiments. The classification ratios for the feature vectors of biological signals and mechanical signals were 94.75% and 97.23%, respectively, when all 16 order LPC vector were used. In order to determine the effect of underwater noise on the classification performance, underwater ambient noise was added to the test signals and the classification ratio according to SNR (signal-to-noise ratio) was compared by changing dimension of feature vector using PCA. The classification ratios of the biological and mechanical signals under ocean ambient noise at 10dB SNR, were 0.51% and 100% respectively. However, the ratios were changed to 53.07% and 83.14% when the dimension of feature vector was converted to three by applying PCA. For correct, classification, it is required SNR over 10 dB for three dimension feature vector and over 30dB SNR for seven dimension feature vector under ocean ambient noise environment.

Keywords

References

  1. 김정태, 류연선, 정성오, 추상훈 (2000). "트러스의 구조손상추정을 위한 진동모드 민감도의 패턴인식", 한국해양공학회지, 제 14권, 제1호, pp 80-87.
  2. 박정현, 배건성, 황찬식 (2007). "시간지연 신경망을 이용한 수중 천이소음 식별", 대한전자공학회 소사이어티 추계학술대회, 제30권, 제2호, pp 575-576.
  3. 임태균 (2007). "위그너-빌 분포함수와 멜 켑스트럼을 이용한 수중 천이신호의 특징 추출 및 식별", 경북대학교 박사학위논문.
  4. Boashash, B. and O'shea, P. (1990). "A Methodology for Detection and Classification of Some Underwater Acoustic Signals using Time Frequency Analysis Techniques", IEEE Transaction on Acoustics, Speech and Signal Processing, Vol 38, No 11, pp 1829-1841. https://doi.org/10.1109/29.103085
  5. Chen, C.H. (1985). "Recongnition of Underwater Transient Patterns" Pattern Recognition, Vol. 18, No. 6, pp 485-490. https://doi.org/10.1016/0031-3203(85)90019-6
  6. Chen, C.H., Lee, J.D. and Lin, M.C. (2000). "Classification of Underwater Signals using Neural Networks", Tamkang Journal of Science and Eng., Vol 3, No 1, pp 31-48.
  7. Clark, C.W., Charif, R., Mitchell, S. and Colby, J. (1996). "Distribution and Behavior of the Bowhead Whales, Balaena Mysticetus, Nased on Prelininary Anlaysis of Acoustic Data Collected During The 1993 Spring Migration off Point Barrow, Alaska", Rep. int. Whal. Commn. Vol 46, pp 541-552.
  8. Clark, C.W., Marler, P. and Beeman, K. (1987). "Quantitative Analysis of aNimal Vocal Phonology: An Application to Swamp Sparrow Song", Ethology, Vol 76, pp 101-115.
  9. Discovery of Sound in the Sea(DOSITS): http://www.dosits.org/audio/interactive/
  10. Gaetz, W., Jantzen, K., Weinberg, H., Spong, P. and Symonds, H. (1993). "A Neural Network Mechanism for Recognition of Individual Orcinus Orca Based on Their Acoustic Behavior: Phase 1", Proc. IEEE Oceans '93, Vol I, pp 455-457.
  11. Hemminger, T.L. and Pao, Y.H. (1994). "Detection and Classification of Underwater Acoustic Transients using Neural Networks", IEEE Transaction on neural networks, Vol 5, No 5, pp 712-718. https://doi.org/10.1109/72.317723
  12. Jiang, X.D., Yan, D.S., Shi, S.G. and Li, S.C. (2006). "The Research on High Speed Underwater Target Recognition Based on Fuzzy Logic Inference" Journal of Marine Science and Application, Vol 5, No 2, pp 19-23. https://doi.org/10.1007/s11804-006-0030-y
  13. Khotanzed, A., Lu, J.H. and Srinath, M.D. (1989). "Target Detection using a Neural Network Based Passice Sonar System", Int. Joint Conference on Neural Networks, Vol I, pp 335-340.
  14. Kicinski, W. (2003). "Processing of Measuring Signals for Monitoring of Transients in Underwater Environment" Proceedings XVII IMEKO World Congress, pp 2098-2101.
  15. Larkin, M. J. (1997). "Classification of Sonar Signals using Baysian Networks", ACSSC 1997, Vol 1, pp 855-858
  16. Learned, R.E. and Willsky, A.S. (1995). "A Wavelet Packet Approach to Transient Signal Classification", Appl. Computat. Harmon. Anal., Vol 2, pp 265-278. https://doi.org/10.1006/acha.1995.1019
  17. Lim, T., Bae, K. and Hwang, C. (2008). "Classification of Underwater Transient Signals using Binary Pattern Image of MFCC and Neural Network", IEICE Transaction on Fundamentals of Electronics, Communications and Computer Sciences, Vol. E91-A, No 3, pp 68-69.
  18. Mellinger, D.K. and Clark, C.W. (2000). "Recongniziong Transient Low-frequency whale Sound by Spectrogram Correlation", J. Acoust. Soc. Am, Vol 107, No 6, pp 3518- 3529. https://doi.org/10.1121/1.429434
  19. Yang, S., Li, Z. and Wang, X. (2002). "Ship Recognition Via its Radiated Sound: The Fractal Based Approaches", J. Acoust. Soc. Am, Vo 112, No 1, pp 172-177. https://doi.org/10.1121/1.1487840

Cited by

  1. Analysis of Features and Discriminability of Transient Signals for a Shallow Water Ambient Noise Environment vol.51, pp.7, 2014, https://doi.org/10.5573/ieie.2014.51.7.209