Automatic Classification of Biological Sounds in the Arctic.
Ambient underwater recordings in the Arctic are generated by a complex mixture of physical processes and biological events. Even for experts, it is difficult and time-consuming to detect and identify biological transients. During this project, improved methods for reviewing multichannel acoustic dat...
Main Author: | |
---|---|
Other Authors: | |
Format: | Text |
Language: | English |
Published: |
1996
|
Subjects: | |
Online Access: | http://www.dtic.mil/docs/citations/ADA329473 http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA329473 |
id |
ftdtic:ADA329473 |
---|---|
record_format |
openpolar |
spelling |
ftdtic:ADA329473 2023-05-15T14:53:38+02:00 Automatic Classification of Biological Sounds in the Arctic. Fristrup, Kurt M. WOODS HOLE OCEANOGRAPHIC INSTITUTION MA 1996-12-31 text/html http://www.dtic.mil/docs/citations/ADA329473 http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA329473 en eng http://www.dtic.mil/docs/citations/ADA329473 APPROVED FOR PUBLIC RELEASE DTIC AND NTIS Biological Oceanography Acoustic Detection and Detectors *ACOUSTIC DATA *AQUATIC ANIMALS TRANSIENTS TWO DIMENSIONAL CLASSIFICATION RECORDING SYSTEMS COLLECTION SONAR SIGNALS UNDERWATER ARCTIC REGIONS MARINE BIOLOGICAL NOISE MULTICHANNEL Text 1996 ftdtic 2016-02-19T20:50:56Z Ambient underwater recordings in the Arctic are generated by a complex mixture of physical processes and biological events. Even for experts, it is difficult and time-consuming to detect and identify biological transients. During this project, improved methods for reviewing multichannel acoustic data and promising techniques for automatic classification of biological sounds were developed. Two analytical methods demonstrated the promise of automatic recognition for these sounds. The first technique was a Classification Tree. This method produced a classifier consisting of a sequence of simple rules based on individual features. A classification tree was computed that divided the collection of sounds into 23 categories; these 22 rules were sufficient to correctly identify 591 of 699 sounds to species, or about 85% correct classification. In addition to the classification tree, a principal component analysis was also conducted on these data. Principal component scores were extracted from the rescaled data, to obtain new features that were mutually orthogonal, and identify which axes expressed the preponderance of the overall variation. The dominant principal component scores were then subjected to a discriminant function analysis, to obtain a set of two-dimensional projections that provide a useful perspective on the distinctiveness of the species' sounds. Text Arctic Defense Technical Information Center: DTIC Technical Reports database Arctic |
institution |
Open Polar |
collection |
Defense Technical Information Center: DTIC Technical Reports database |
op_collection_id |
ftdtic |
language |
English |
topic |
Biological Oceanography Acoustic Detection and Detectors *ACOUSTIC DATA *AQUATIC ANIMALS TRANSIENTS TWO DIMENSIONAL CLASSIFICATION RECORDING SYSTEMS COLLECTION SONAR SIGNALS UNDERWATER ARCTIC REGIONS MARINE BIOLOGICAL NOISE MULTICHANNEL |
spellingShingle |
Biological Oceanography Acoustic Detection and Detectors *ACOUSTIC DATA *AQUATIC ANIMALS TRANSIENTS TWO DIMENSIONAL CLASSIFICATION RECORDING SYSTEMS COLLECTION SONAR SIGNALS UNDERWATER ARCTIC REGIONS MARINE BIOLOGICAL NOISE MULTICHANNEL Fristrup, Kurt M. Automatic Classification of Biological Sounds in the Arctic. |
topic_facet |
Biological Oceanography Acoustic Detection and Detectors *ACOUSTIC DATA *AQUATIC ANIMALS TRANSIENTS TWO DIMENSIONAL CLASSIFICATION RECORDING SYSTEMS COLLECTION SONAR SIGNALS UNDERWATER ARCTIC REGIONS MARINE BIOLOGICAL NOISE MULTICHANNEL |
description |
Ambient underwater recordings in the Arctic are generated by a complex mixture of physical processes and biological events. Even for experts, it is difficult and time-consuming to detect and identify biological transients. During this project, improved methods for reviewing multichannel acoustic data and promising techniques for automatic classification of biological sounds were developed. Two analytical methods demonstrated the promise of automatic recognition for these sounds. The first technique was a Classification Tree. This method produced a classifier consisting of a sequence of simple rules based on individual features. A classification tree was computed that divided the collection of sounds into 23 categories; these 22 rules were sufficient to correctly identify 591 of 699 sounds to species, or about 85% correct classification. In addition to the classification tree, a principal component analysis was also conducted on these data. Principal component scores were extracted from the rescaled data, to obtain new features that were mutually orthogonal, and identify which axes expressed the preponderance of the overall variation. The dominant principal component scores were then subjected to a discriminant function analysis, to obtain a set of two-dimensional projections that provide a useful perspective on the distinctiveness of the species' sounds. |
author2 |
WOODS HOLE OCEANOGRAPHIC INSTITUTION MA |
format |
Text |
author |
Fristrup, Kurt M. |
author_facet |
Fristrup, Kurt M. |
author_sort |
Fristrup, Kurt M. |
title |
Automatic Classification of Biological Sounds in the Arctic. |
title_short |
Automatic Classification of Biological Sounds in the Arctic. |
title_full |
Automatic Classification of Biological Sounds in the Arctic. |
title_fullStr |
Automatic Classification of Biological Sounds in the Arctic. |
title_full_unstemmed |
Automatic Classification of Biological Sounds in the Arctic. |
title_sort |
automatic classification of biological sounds in the arctic. |
publishDate |
1996 |
url |
http://www.dtic.mil/docs/citations/ADA329473 http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA329473 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_source |
DTIC AND NTIS |
op_relation |
http://www.dtic.mil/docs/citations/ADA329473 |
op_rights |
APPROVED FOR PUBLIC RELEASE |
_version_ |
1766325229370474496 |