Comparing Performances of Five Distinct Automatic Classifiers for Fin Whale Vocalizations in Beamformed Spectrograms of Coherent Hydrophone Array
A large variety of sound sources in the ocean, including biological, geophysical, and man-made, can be simultaneously monitored over instantaneous continental-shelf scale regions via the passive ocean acoustic waveguide remote sensing (POAWRS) technique by employing a large-aperture densely-populate...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2020
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs12020326 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/12/2/326/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/12/2/326/ 2023-08-20T04:06:28+02:00 Comparing Performances of Five Distinct Automatic Classifiers for Fin Whale Vocalizations in Beamformed Spectrograms of Coherent Hydrophone Array Heriberto A. Garcia Trenton Couture Amit Galor Jessica M. Topple Wei Huang Devesh Tiwari Purnima Ratilal agris 2020-01-19 application/pdf https://doi.org/10.3390/rs12020326 EN eng Multidisciplinary Digital Publishing Institute Ocean Remote Sensing https://dx.doi.org/10.3390/rs12020326 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 12; Issue 2; Pages: 326 fin whale vocalization classification neural networks 20 Hz CNN LSTM passive ocean acoustic waveguide remote sensing POAWRS marine mammal decision tree logistic regression support vector machine chirp Text 2020 ftmdpi https://doi.org/10.3390/rs12020326 2023-07-31T23:01:05Z A large variety of sound sources in the ocean, including biological, geophysical, and man-made, can be simultaneously monitored over instantaneous continental-shelf scale regions via the passive ocean acoustic waveguide remote sensing (POAWRS) technique by employing a large-aperture densely-populated coherent hydrophone array system. Millions of acoustic signals received on the POAWRS system per day can make it challenging to identify individual sound sources. An automated classification system is necessary to enable sound sources to be recognized. Here, the objectives are to (i) gather a large training and test data set of fin whale vocalization and other acoustic signal detections; (ii) build multiple fin whale vocalization classifiers, including a logistic regression, support vector machine (SVM), decision tree, convolutional neural network (CNN), and long short-term memory (LSTM) network; (iii) evaluate and compare performance of these classifiers using multiple metrics including accuracy, precision, recall and F1-score; and (iv) integrate one of the classifiers into the existing POAWRS array and signal processing software. The findings presented here will (1) provide an automatic classifier for near real-time fin whale vocalization detection and recognition, useful in marine mammal monitoring applications; and (2) lay the foundation for building an automatic classifier applied for near real-time detection and recognition of a wide variety of biological, geophysical, and man-made sound sources typically detected by the POAWRS system in the ocean. Text Fin whale Marine Mammal Monitoring MDPI Open Access Publishing Remote Sensing 12 2 326 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
fin whale vocalization classification neural networks 20 Hz CNN LSTM passive ocean acoustic waveguide remote sensing POAWRS marine mammal decision tree logistic regression support vector machine chirp |
spellingShingle |
fin whale vocalization classification neural networks 20 Hz CNN LSTM passive ocean acoustic waveguide remote sensing POAWRS marine mammal decision tree logistic regression support vector machine chirp Heriberto A. Garcia Trenton Couture Amit Galor Jessica M. Topple Wei Huang Devesh Tiwari Purnima Ratilal Comparing Performances of Five Distinct Automatic Classifiers for Fin Whale Vocalizations in Beamformed Spectrograms of Coherent Hydrophone Array |
topic_facet |
fin whale vocalization classification neural networks 20 Hz CNN LSTM passive ocean acoustic waveguide remote sensing POAWRS marine mammal decision tree logistic regression support vector machine chirp |
description |
A large variety of sound sources in the ocean, including biological, geophysical, and man-made, can be simultaneously monitored over instantaneous continental-shelf scale regions via the passive ocean acoustic waveguide remote sensing (POAWRS) technique by employing a large-aperture densely-populated coherent hydrophone array system. Millions of acoustic signals received on the POAWRS system per day can make it challenging to identify individual sound sources. An automated classification system is necessary to enable sound sources to be recognized. Here, the objectives are to (i) gather a large training and test data set of fin whale vocalization and other acoustic signal detections; (ii) build multiple fin whale vocalization classifiers, including a logistic regression, support vector machine (SVM), decision tree, convolutional neural network (CNN), and long short-term memory (LSTM) network; (iii) evaluate and compare performance of these classifiers using multiple metrics including accuracy, precision, recall and F1-score; and (iv) integrate one of the classifiers into the existing POAWRS array and signal processing software. The findings presented here will (1) provide an automatic classifier for near real-time fin whale vocalization detection and recognition, useful in marine mammal monitoring applications; and (2) lay the foundation for building an automatic classifier applied for near real-time detection and recognition of a wide variety of biological, geophysical, and man-made sound sources typically detected by the POAWRS system in the ocean. |
format |
Text |
author |
Heriberto A. Garcia Trenton Couture Amit Galor Jessica M. Topple Wei Huang Devesh Tiwari Purnima Ratilal |
author_facet |
Heriberto A. Garcia Trenton Couture Amit Galor Jessica M. Topple Wei Huang Devesh Tiwari Purnima Ratilal |
author_sort |
Heriberto A. Garcia |
title |
Comparing Performances of Five Distinct Automatic Classifiers for Fin Whale Vocalizations in Beamformed Spectrograms of Coherent Hydrophone Array |
title_short |
Comparing Performances of Five Distinct Automatic Classifiers for Fin Whale Vocalizations in Beamformed Spectrograms of Coherent Hydrophone Array |
title_full |
Comparing Performances of Five Distinct Automatic Classifiers for Fin Whale Vocalizations in Beamformed Spectrograms of Coherent Hydrophone Array |
title_fullStr |
Comparing Performances of Five Distinct Automatic Classifiers for Fin Whale Vocalizations in Beamformed Spectrograms of Coherent Hydrophone Array |
title_full_unstemmed |
Comparing Performances of Five Distinct Automatic Classifiers for Fin Whale Vocalizations in Beamformed Spectrograms of Coherent Hydrophone Array |
title_sort |
comparing performances of five distinct automatic classifiers for fin whale vocalizations in beamformed spectrograms of coherent hydrophone array |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2020 |
url |
https://doi.org/10.3390/rs12020326 |
op_coverage |
agris |
genre |
Fin whale Marine Mammal Monitoring |
genre_facet |
Fin whale Marine Mammal Monitoring |
op_source |
Remote Sensing; Volume 12; Issue 2; Pages: 326 |
op_relation |
Ocean Remote Sensing https://dx.doi.org/10.3390/rs12020326 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs12020326 |
container_title |
Remote Sensing |
container_volume |
12 |
container_issue |
2 |
container_start_page |
326 |
_version_ |
1774717524771864576 |