A novel modeling and recognition method for underwater sound based on HMT in wavelet domain

  • Authors:

  • Zhou Yue;Kong Wei;Xu Qing

  • Affiliations:

  • Institute of Image Processing & Pattern Recognition, SJTU, China;Institute of Image Processing & Pattern Recognition, SJTU, China;Institute of Image Processing & Pattern Recognition, SJTU, China

  • Venue:
  • AI'04 Proceedings of the 17th Australian joint conference on Advances in Artificial Intelligence
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

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.