Accession Number : ADA321626
Title : Classification of Ocean Acoustic Data Using AR Modeling and Wavelet Transforms.
Descriptive Note : Rept. for Dec 94-Jun 96,
Corporate Author : NAVAL POSTGRADUATE SCHOOL MONTEREY CA DEPT OF ELECTRICAL AND COMPUTER ENGINEE RING
Personal Author(s) : Fargues, M. P. ; Bennett, R. ; Barsanti, R. J.
PDF Url : ADA321626
Report Date : JAN 1997
Pagination or Media Count : 42
Abstract : This study investigates the application of orthogonal, non-orthogonal wavelet-based procedures, and AR modeling as feature extraction techniques to classify several classes of underwater signals consisting of sperm whale, killer whale, gray whale, pilot whale, humpback whale, and underwater earthquake data. A two-hidden-layer back-propagation neural network is used for the classification procedure. Performance obtained using the two wavelet-based schemes are compared with those obtained using reduced-rank AR modeling tools. Results show that the non-orthogonal undecimated A-trous implementation with multiple voices leads to the highest classification rate of 96.7%.
Descriptors : *ACOUSTIC DATA, *UNDERWATER SOUND SIGNALS, REGRESSION ANALYSIS, OCEANOGRAPHIC DATA, CLASSIFICATION, EARTHQUAKES, MARINE BIOLOGICAL NOISE, WAVELET TRANSFORMS.
Subject Categories : Acoustic Detection and Detectors
Distribution Statement : APPROVED FOR PUBLIC RELEASE