Affiliation:
1. Chuxiong Normal University
2. Kunming Institute of Physics
Abstract
A feature extraction method based on wavelet packet energy distribution and correlation coefficient has been put forward to recognize the different acoustic targets in this paper. In view of the characteristics of acoustic target, we employed principal component analysis (PCA) to compress data set of the features extracted based on wavelet packet energy distribution and correlation coefficient. The results have been inputted into the neural network as eigenvectors for pattern recognition. Simulation results indicate that the method suggested in this paper have a recognition rate better than 8% with only wavelet packet energy method, thus verifying its effectiveness .
Publisher
Trans Tech Publications, Ltd.
Reference6 articles.
1. Michael V. Namorato. A concise history of acoustics in warfare. Applied Acoustics. 59 (2000): 101～135.
2. Dr. Russell Braunling, Randy M. Jensen, Michael A. Gallo. Acoustic target detection, tracking, classification, and location in a multiple target environment. Proceedings of SPIE. Vol. 3081, (1997): 57～66.
3. Lü yong lin . Research and realization of system of acoustic target recognition. Tian jin: Tian jin university, (2007).
4. Fan Haining, Guo Ying, Wu J ianfeng, Chen Zhiwu. Abstract ion of sound signal characterist ics based on wavelet packet decomposition . Moden electrice tehcnique 2005(4): 20~21.
5. Fan jincheng, Mei changlin. Data analysis. Beijing: Science Press, (2002).