Abstract
To modeling and classify underwater sound, hidden Markov tree (HMT) model in wavelet domain is adopted. Taking advantage of the models, the simulation time sequence of ocean noise can be produced. An improved classification approach based on HMT model and fuzzy maximum and minimum neural net work (FMMNN) is brought forward, which integrates the wavelet coefficients HMT models with FMMNN. The performance of this approach is evaluated experimentally in classifying four types of ocean noises. With an accuracy of more than 86%, this HMT-based approach is found to outperform previously proposed classifiers. Experiments prove that the new method is effective.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Urick, R.J.: Priciples of Underwater Sound, 3rd edn. McGraw Hill Book Company, New York (1983)
Donoho, D., Johnstone, I.: Adapting to unknown Smoothness via Wavelet Shrinkage, J. Amer. Stat. Assoc. 90, 1200–1224 (1995)
Crouse, M.S., et al.: Wavelet-Based Statistical Signal Processing Using Hidden Markov Models. IEEE Trans. Signal Processing 46, 886–902 (1998)
Simpson, P.K.: Fuzzy Min-Max networks-part 1: classification. IEEE Trans., on Neural Networks 3, 776–786 (1992)
Simpson, P.K.: Fuzzy Min-Max networks-part 2: clustering. IEEE Trans., on Fuzzy Systems 1, 32–45 (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yue, Z., Wei, K., Qing, X. (2004). A Novel Modeling and Recognition Method for Underwater Sound Based on HMT in Wavelet Domain. In: Webb, G.I., Yu, X. (eds) AI 2004: Advances in Artificial Intelligence. AI 2004. Lecture Notes in Computer Science(), vol 3339. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30549-1_30
Download citation
DOI: https://doi.org/10.1007/978-3-540-30549-1_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-24059-4
Online ISBN: 978-3-540-30549-1
eBook Packages: Computer ScienceComputer Science (R0)