Sonar signal classification using the BCM learning algorithm

Author

Larkin, Michael J.

Author_Institution

Naval Undersea Warfare Center, Newport, RI, USA

fYear

1996

fDate

3-6 Nov. 1996

Firstpage

844

Abstract

Previous work by the author has demonstrated the capability of the Bienenstock Cooper Munro (BCM) model (proposed in 1982) of neural synaptic modification to perform feature extraction, thus enhancing the performance of automated classifiers. Recent work has applied the BCM algorithm to sonar images of minelike objects, with the output of the BCM networks fed into a neural network classifier. This paper demonstrates the capability of this approach to classify, objects as minelike or non-minelike, and to further classify the minelike objects by type.

Keywords

feature extraction; image classification; learning (artificial intelligence); military equipment; neural nets; sonar imaging; BCM learning algorithm; Bienenstock Cooper Munro model; acoustic signal classification; automated classifiers; feature extraction; minelike objects; neural network classifier; neural synaptic modification; nonminelike objects; object classification; performance enhancement; sonar images; sonar signal classification; Convolution; Feature extraction; Feedforward systems; Neural networks; Neurons; Pattern classification; Signal processing; Sonar applications; Sonar detection; Underwater acoustics;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 1996. Conference Record of the Thirtieth Asilomar Conference on

Conference_Location

Pacific Grove, CA, USA

ISSN

1058-6393

Print_ISBN

0-8186-7646-9

Type

conf

DOI

10.1109/ACSSC.1996.599063

Filename

599063