Skip navigation
Skip navigation

Assemblage of Focal Species Recognizers-AFSR: A technique for decreasing false indications of presence from acoustic automatic identification in a multiple species context

Campos, Ivan Braga; Landers, T J; Lee, Kate D.; Lee, William George; Friesen, Megan R; Gaskett, A. C; Ranjard, Louis

Description

Passive acoustic monitoring (PAM) coupled with automated species identification is a promising tool for species monitoring and conservation worldwide. However, high false indications of presence are still an important limitation and a crucial factor for acceptance of these techniques in wildlife surveys. Here we present the Assemblage of Focal Species Recognizers—AFSR, a novel approach for decreasing false positives and increasing models’ precision in multispecies contexts. AFSR focusses on...[Show more]

dc.contributor.authorCampos, Ivan Braga
dc.contributor.authorLanders, T J
dc.contributor.authorLee, Kate D.
dc.contributor.authorLee, William George
dc.contributor.authorFriesen, Megan R
dc.contributor.authorGaskett, A. C
dc.contributor.authorRanjard, Louis
dc.date.accessioned2021-03-18T00:17:07Z
dc.date.available2021-03-18T00:17:07Z
dc.identifier.issn1932-6203
dc.identifier.urihttp://hdl.handle.net/1885/227269
dc.description.abstractPassive acoustic monitoring (PAM) coupled with automated species identification is a promising tool for species monitoring and conservation worldwide. However, high false indications of presence are still an important limitation and a crucial factor for acceptance of these techniques in wildlife surveys. Here we present the Assemblage of Focal Species Recognizers—AFSR, a novel approach for decreasing false positives and increasing models’ precision in multispecies contexts. AFSR focusses on decreasing false positives by excluding unreliable sound file segments that are prone to misidentification. We used MatlabHTK, a hidden Markov models interface for bioacoustics analyses, for illustrating AFSR technique by comparing two approaches, 1) a multispecies recognizer where all species are identified simultaneously, and 2) an assemblage of focal species recognizers (AFSR), where several recognizers that each prioritise a single focal species are then summarised into a single output, according to a set of rules designed to exclude unreliable segments. Both approaches (the multispecies recognizer and AFSR) used the same sound files training dataset, but different processing workflow. We applied these recognisers to PAM recordings from a remote island colony with five seabird species and compared their outputs with manual species identifications. False positives and precision improved for all the five species when using AFSR, achieving remarkable 0% false positives and 100% precision for three of five seabird species, and < 6% false positives, and >90% precision for the other two species. AFSR’ output was also used to generate daily calling activity patterns for each species. Instead of attempting to withdraw useful information from every fragment in a sound recording, AFSR prioritises more trustworthy information from sections with better quality data. AFSR can be applied to automated species identification from multispecies PAM recordings worldwide.
dc.description.sponsorshipIBC received a Science Without Borders PhD scholarship funded by CNPq-Brazil.
dc.format.mimetypeapplication/pdf
dc.language.isoen_AU
dc.publisherPublic Library of Science
dc.rights© 2019 Campos et al.
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.sourcePLOS ONE
dc.titleAssemblage of Focal Species Recognizers-AFSR: A technique for decreasing false indications of presence from acoustic automatic identification in a multiple species context
dc.typeJournal article
local.description.notesImported from ARIES
local.identifier.citationvolume14
dc.date.issued2019
local.identifier.absfor060412 - Quantitative Genetics (incl. Disease and Trait Mapping Genetics)
local.identifier.ariespublicationa383154xPUB11866
local.publisher.urlhttp://www.plosone.org/
local.type.statusPublished Version
local.contributor.affiliationCampos, Ivan Braga, University of Auckland
local.contributor.affiliationLanders, T J, Univeristy of Auckland
local.contributor.affiliationLee, Kate D., University of Auckland
local.contributor.affiliationLee, William George, School of Biological Sciences
local.contributor.affiliationFriesen, Megan R, University of Auckland
local.contributor.affiliationGaskett, A. C , The University of Auckland
local.contributor.affiliationRanjard, Louis, College of Science, ANU
local.bibliographicCitation.issue12
local.bibliographicCitation.startpagee0212727
local.identifier.doi10.1371/journal.pone.0212727
local.identifier.absseo970106 - Expanding Knowledge in the Biological Sciences
dc.date.updated2020-11-22T07:18:43Z
dcterms.accessRightsOpen Access
dc.provenanceThis is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
dc.rights.licenseCreative Commons Attribution License
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Campos_Assemblage_of_Focal_Species_2019.pdf2.15 MBAdobe PDFThumbnail


This item is licensed under a Creative Commons License Creative Commons

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator