DEEP LEARNING TECHNIQUES FOR SHIPBOARD SOUNDSCAPE CLASSIFICATION
Loading...
Authors
Delaney, Kevin J.
Subjects
deep learning
convolutional neural network
wavelet
fourier transform
acoustic
soundscape
OSAM
convolutional neural network
wavelet
fourier transform
acoustic
soundscape
OSAM
Advisors
Orescanin, Marko
Date of Issue
2025-03
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
The Navy is seeking to remedy a perceived lack of innovation in the field of acoustic soundscape classification by investing in deep learning classification techniques to implement in own-ship acoustic monitoring (OSAM) applications. Data used from a Naval Surface Warfare Center (Carderock Division) (NSWCCD) was modeled and classified using deep-learning methods, with both mel-scaled short-time Fourier-transformed and wavelet-transformed soundscape data. These models were then compared to similarly-transformed urban environmental soundscape data. Results show that convolutional neural networks are capable of classifying shipboard soundscapes effectively, with 99% classification accuracy, and are perhaps even more capable with shipboard data than other urban environmental soundscapes.
Type
Thesis
Description
Series/Report No
Department
Organization
Identifiers
NPS Report Number
Sponsors
Funding
Format
Citation
Distribution Statement
Distribution Statement A. Approved for public release: Distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.