Classification of Ocean Acoustic Data Using AR Modeling and Wavelet Transforms

• Main Authors: Fargues, Monique P., Bennett, R., Barsanti, R.J.
• Other Authors: Electrical and Computer Engineering (ECE), Graduate School of Engineering and Applied Science (GSEAS), Electrical and Computer Engineering
• Format: Report
• Language: unknown
• Published: Monterey, California. Naval Postgraduate School 1997
• Subjects: wavelet transform; AR modeling; classification; Humpback Whale; Killer Whale; Sperm whale; Killer whale
• Online Access: https://hdl.handle.net/10945/15299

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% Approved for public release; distribution is unlimited. N0002495WR10820 Naval Undersea Warfare Center, Newport Division