Share Email Print

Proceedings Paper

Comparison of confidence level of different classification paradigms for underwater target discrimination
Author(s): Donghui Li; Mahmood R. Azimi-Sadjadi; Arta A. Jamshidi; Gerald J. Dobeck
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The problem of classification of underwater targets from the acoustic backscattered signals is considered. A wavelet packet-based feature extraction scheme is used in conjunction with the linear prediction coding (LPC) scheme as the front-end processor. Selected features with higher discriminatory power are then fed to a neural network classifier. Several different classification system are benchmarked in this paper. These include: an ellipsoidal K- nearest neighbor classifier, probabilistic neural networks and support vector machines. The performance of these classifiers are examined on a wideband 80 kHz acoustic backscattered data set collected for six different objects. These systems are then benchmarked with the previously used Back propagation Neural Network in terms of their receiver operating characteristics and robustness with respect to reverberation.

Paper Details

Date Published: 18 October 2001
PDF: 12 pages
Proc. SPIE 4394, Detection and Remediation Technologies for Mines and Minelike Targets VI, (18 October 2001); doi: 10.1117/12.445443
Show Author Affiliations
Donghui Li, Colorado State Univ. (United States)
Mahmood R. Azimi-Sadjadi, Colorado State Univ. (United States)
Arta A. Jamshidi, Colorado State Univ. (United States)
Gerald J. Dobeck, Naval Surface Warfare Ctr. (United States)

Published in SPIE Proceedings Vol. 4394:
Detection and Remediation Technologies for Mines and Minelike Targets VI
Abinash C. Dubey; James F. Harvey; J. Thomas Broach; Vivian George, Editor(s)

© SPIE. Terms of Use
Back to Top