Porpoise click classifier (PorCC):A high-accuracy classifier to study harbour porpoises (Phocoena phocoena) in the wild

Harbour porpoises are well-suited for passive acoustic monitoring (PAM) as they produce highly stereotyped narrow-band high-frequency (NBHF) echolocation clicks. PAM systems must be coupled with a classification algorithm to identify the signals of interest. Here, the authors present a harbour porpo...

Full description

Bibliographic Details
Published in:The Journal of the Acoustical Society of America
Main Authors: Cosentino, Mel, Guarato, Francesco, Tougaard, Jakob, Nairn, David, Jackson, Joseph C., Windmill, James F.C.
Format: Article in Journal/Newspaper
Language:English
Published: 2019
Subjects:
Online Access:https://pure.au.dk/portal/da/publications/porpoise-click-classifier-porcc(f14ad71c-76fd-4321-b787-9faadaa82771).html
https://doi.org/10.1121/1.5110908
https://pure.au.dk/ws/files/198663042/Porpoise_click.pdf
http://www.scopus.com/inward/record.url?scp=85067297642&partnerID=8YFLogxK
id ftuniaarhuspubl:oai:pure.atira.dk:publications/f14ad71c-76fd-4321-b787-9faadaa82771
record_format openpolar
spelling ftuniaarhuspubl:oai:pure.atira.dk:publications/f14ad71c-76fd-4321-b787-9faadaa82771 2023-06-11T04:12:26+02:00 Porpoise click classifier (PorCC):A high-accuracy classifier to study harbour porpoises (Phocoena phocoena) in the wild Cosentino, Mel Guarato, Francesco Tougaard, Jakob Nairn, David Jackson, Joseph C. Windmill, James F.C. 2019-06 application/pdf https://pure.au.dk/portal/da/publications/porpoise-click-classifier-porcc(f14ad71c-76fd-4321-b787-9faadaa82771).html https://doi.org/10.1121/1.5110908 https://pure.au.dk/ws/files/198663042/Porpoise_click.pdf http://www.scopus.com/inward/record.url?scp=85067297642&partnerID=8YFLogxK eng eng info:eu-repo/semantics/openAccess Cosentino , M , Guarato , F , Tougaard , J , Nairn , D , Jackson , J C & Windmill , J F C 2019 , ' Porpoise click classifier (PorCC) : A high-accuracy classifier to study harbour porpoises (Phocoena phocoena) in the wild ' , Acoustical Society of America. Journal , vol. 145 , no. 6 , pp. 3427-3434 . https://doi.org/10.1121/1.5110908 article 2019 ftuniaarhuspubl https://doi.org/10.1121/1.5110908 2023-05-10T22:57:27Z Harbour porpoises are well-suited for passive acoustic monitoring (PAM) as they produce highly stereotyped narrow-band high-frequency (NBHF) echolocation clicks. PAM systems must be coupled with a classification algorithm to identify the signals of interest. Here, the authors present a harbour porpoise click classifier (PorCC) developed in matlab, which uses the coefficients of two logistic regression models in a decision-making pathway to assign candidate signals to one of three categories: High-quality clicks (HQ), low-quality clicks (LQ), or high-frequency noise. The receiver operating characteristics of PorCC was compared to that of PAMGuard's Porpoise Click Detector/Classifier Module. PorCC outperformed PAMGuard's classifier achieving higher hit rates (correctly classified clicks) and lower false alarm levels (noise classified as HQ or LQ clicks). Additionally, the detectability index (d′) for HQ clicks for PAMGuard was 2.2 (overall d′ = 2.0) versus 4.1 for PorCC (overall d′ = 3.4). PorCC classification algorithm is a rapid and highly accurate method to classify NBHF clicks, which could be applied for real time monitoring, as well as to study harbour porpoises, and potentially other NBHF species, throughout their distribution range from data collected using towed hydrophones or static recorders. Moreover, PorCC is suitable for studies of acoustic communication of porpoises. Article in Journal/Newspaper Harbour porpoise Phocoena phocoena Aarhus University: Research The Journal of the Acoustical Society of America 145 6 3427 3434
institution Open Polar
collection Aarhus University: Research
op_collection_id ftuniaarhuspubl
language English
description Harbour porpoises are well-suited for passive acoustic monitoring (PAM) as they produce highly stereotyped narrow-band high-frequency (NBHF) echolocation clicks. PAM systems must be coupled with a classification algorithm to identify the signals of interest. Here, the authors present a harbour porpoise click classifier (PorCC) developed in matlab, which uses the coefficients of two logistic regression models in a decision-making pathway to assign candidate signals to one of three categories: High-quality clicks (HQ), low-quality clicks (LQ), or high-frequency noise. The receiver operating characteristics of PorCC was compared to that of PAMGuard's Porpoise Click Detector/Classifier Module. PorCC outperformed PAMGuard's classifier achieving higher hit rates (correctly classified clicks) and lower false alarm levels (noise classified as HQ or LQ clicks). Additionally, the detectability index (d′) for HQ clicks for PAMGuard was 2.2 (overall d′ = 2.0) versus 4.1 for PorCC (overall d′ = 3.4). PorCC classification algorithm is a rapid and highly accurate method to classify NBHF clicks, which could be applied for real time monitoring, as well as to study harbour porpoises, and potentially other NBHF species, throughout their distribution range from data collected using towed hydrophones or static recorders. Moreover, PorCC is suitable for studies of acoustic communication of porpoises.
format Article in Journal/Newspaper
author Cosentino, Mel
Guarato, Francesco
Tougaard, Jakob
Nairn, David
Jackson, Joseph C.
Windmill, James F.C.
spellingShingle Cosentino, Mel
Guarato, Francesco
Tougaard, Jakob
Nairn, David
Jackson, Joseph C.
Windmill, James F.C.
Porpoise click classifier (PorCC):A high-accuracy classifier to study harbour porpoises (Phocoena phocoena) in the wild
author_facet Cosentino, Mel
Guarato, Francesco
Tougaard, Jakob
Nairn, David
Jackson, Joseph C.
Windmill, James F.C.
author_sort Cosentino, Mel
title Porpoise click classifier (PorCC):A high-accuracy classifier to study harbour porpoises (Phocoena phocoena) in the wild
title_short Porpoise click classifier (PorCC):A high-accuracy classifier to study harbour porpoises (Phocoena phocoena) in the wild
title_full Porpoise click classifier (PorCC):A high-accuracy classifier to study harbour porpoises (Phocoena phocoena) in the wild
title_fullStr Porpoise click classifier (PorCC):A high-accuracy classifier to study harbour porpoises (Phocoena phocoena) in the wild
title_full_unstemmed Porpoise click classifier (PorCC):A high-accuracy classifier to study harbour porpoises (Phocoena phocoena) in the wild
title_sort porpoise click classifier (porcc):a high-accuracy classifier to study harbour porpoises (phocoena phocoena) in the wild
publishDate 2019
url https://pure.au.dk/portal/da/publications/porpoise-click-classifier-porcc(f14ad71c-76fd-4321-b787-9faadaa82771).html
https://doi.org/10.1121/1.5110908
https://pure.au.dk/ws/files/198663042/Porpoise_click.pdf
http://www.scopus.com/inward/record.url?scp=85067297642&partnerID=8YFLogxK
genre Harbour porpoise
Phocoena phocoena
genre_facet Harbour porpoise
Phocoena phocoena
op_source Cosentino , M , Guarato , F , Tougaard , J , Nairn , D , Jackson , J C & Windmill , J F C 2019 , ' Porpoise click classifier (PorCC) : A high-accuracy classifier to study harbour porpoises (Phocoena phocoena) in the wild ' , Acoustical Society of America. Journal , vol. 145 , no. 6 , pp. 3427-3434 . https://doi.org/10.1121/1.5110908
op_rights info:eu-repo/semantics/openAccess
op_doi https://doi.org/10.1121/1.5110908
container_title The Journal of the Acoustical Society of America
container_volume 145
container_issue 6
container_start_page 3427
op_container_end_page 3434
_version_ 1768388306738872320