A neural network-based passive sonar detection and classification design with a low false alarm rate

Author

Casselman, Frederick L. ; Freeman, David F. ; Kerrigan, Debra A. ; Lane, Scott E. ; Millstrom, Nancy H. ; Nichols, Wesley G., Jr.

Author_Institution

GTE Gov. Syst., Needham, MA, USA

fYear

1991

fDate

15-17 Aug 1991

Firstpage

49

Lastpage

55

Abstract

The Standard Transient Data Set (STDS) Phase 1 data were used to design detection and classification algorithms. Two separate processing chains were constructed, using neural networks for the short-duration transients and conventional processing for tonals. The design activity emphasized the judicious matching of acoustic digital signal processing (DSP) and neural networks, plus the construction of optimized training sets. The resulting design achieved 92% correct classification of the events in the testing files (204 correct out of 221 total events), with only four false alarms in approximately 35 min of data

Keywords

acoustic signal processing; neural nets; pattern recognition; signal detection; sonar; underwater sound; Standard Transient Data Set; acoustic digital signal processing; classification algorithms; low false alarm rate; neural network-based passive sonar detection; optimized training sets; short-duration transients; tonals; transients; Acoustic signal detection; Algorithm design and analysis; Classification algorithms; Design optimization; Digital signal processing; Neural networks; Phase detection; Signal design; Signal processing algorithms; Sonar detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Ocean Engineering, 1991., IEEE Conference on

Conference_Location

Washington, DC

Print_ISBN

0-7803-0205-2

Type

conf

DOI

10.1109/ICNN.1991.163326

Filename

163326