No Cover Image

Journal article 521 views 60 downloads

Quantifying allo-grooming in wild chacma baboons (Papio ursinus) using tri-axial acceleration data and machine learning

Charlotte Christensen, Anna Bracken, M. Justin O'Riain Orcid Logo, Gaëlle Fehlmann Orcid Logo, Mark Holton Orcid Logo, Phillip Hopkins Orcid Logo, Andrew King Orcid Logo, Ines Fuertbauer Orcid Logo

Royal Society Open Science, Volume: 10, Issue: 4

Swansea University Authors: Charlotte Christensen, Anna Bracken, Mark Holton Orcid Logo, Phillip Hopkins Orcid Logo, Andrew King Orcid Logo, Ines Fuertbauer Orcid Logo

  • 62974.VOR.pdf

    PDF | Version of Record

    Distributed under the terms of a Creative Commons Attribution 4.0 License.

    Download (1.06MB)

Check full text

DOI (Published version): 10.1098/rsos.221103

Abstract

Quantification of activity budgets is pivotal for understanding how animals respond to changes in their environment. Social grooming is a key activity that underpins various social processes with consequences for health and fitness. Traditional methods use direct (focal) observations to calculate gr...

Full description

Published in: Royal Society Open Science
ISSN: 2054-5703
Published: The Royal Society 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa62974
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2023-04-14T12:04:25Z
last_indexed 2023-04-15T03:22:25Z
id cronfa62974
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>62974</id><entry>2023-03-17</entry><title>Quantifying allo-grooming in wild chacma baboons (Papio ursinus) using tri-axial acceleration data and machine learning</title><swanseaauthors><author><sid>707c5165eb55a87ab23bc5bb9a10826f</sid><firstname>Charlotte</firstname><surname>Christensen</surname><name>Charlotte Christensen</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>cfca3b883779efc03ecf86352832b39f</sid><firstname>Anna</firstname><surname>Bracken</surname><name>Anna Bracken</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>0e1d89d0cc934a740dcd0a873aed178e</sid><ORCID>0000-0001-8834-3283</ORCID><firstname>Mark</firstname><surname>Holton</surname><name>Mark Holton</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>cdb0ce5ff78d21e34aac34445b4a4c57</sid><ORCID>0009-0005-6570-6236</ORCID><firstname>Phillip</firstname><surname>Hopkins</surname><name>Phillip Hopkins</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>cc115b4bc4672840f960acc1cb078642</sid><ORCID>0000-0002-6870-9767</ORCID><firstname>Andrew</firstname><surname>King</surname><name>Andrew King</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>f682ec95fa97c4fabb57dc098a9fdaaa</sid><ORCID>0000-0003-1404-6280</ORCID><firstname>Ines</firstname><surname>Fuertbauer</surname><name>Ines Fuertbauer</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-03-17</date><deptcode>SBI</deptcode><abstract>Quantification of activity budgets is pivotal for understanding how animals respond to changes in their environment. Social grooming is a key activity that underpins various social processes with consequences for health and fitness. Traditional methods use direct (focal) observations to calculate grooming rates, providing systematic but sparse data. Accelerometers, in contrast, can quantify activity budgets continuously but have not been used to quantify social grooming. We test whether grooming can be accurately identified using machine learning (random forest model) trained on labelled acceleration data from wild chacma baboons (Papio ursinus). We successfully identified giving and receiving grooming with high precision (81% and 91%) and recall (87% and 79%). Giving grooming was associated with a distinct rhythmical signal along the surge axis. Receiving grooming had similar acceleration signals to resting, and thus was more difficult to assign. We applied our machine learning model to n = 680 collar data days from n = 12 baboons and found that grooming rates obtained from accelerometers were significantly and positively correlated with direct observation rates for giving but not receiving grooming. The ability to collect continuous grooming data in wild populations will allow researchers to re-examine and expand upon long-standing questions regarding the formation and function of grooming bonds.</abstract><type>Journal Article</type><journal>Royal Society Open Science</journal><volume>10</volume><journalNumber>4</journalNumber><paginationStart/><paginationEnd/><publisher>The Royal Society</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2054-5703</issnElectronic><keywords>machine learning, tri-axial accelerometers, random forest models, allo-grooming, activity budgets, primates</keywords><publishedDay>1</publishedDay><publishedMonth>4</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-04-01</publishedDate><doi>10.1098/rsos.221103</doi><url>http://dx.doi.org/10.1098/rsos.221103</url><notes/><college>COLLEGE NANME</college><department>Biosciences</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SBI</DepartmentCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>Swansea University, NRF Incentive Funding</funders><projectreference/><lastEdited>2023-06-23T15:41:17.5261595</lastEdited><Created>2023-03-17T09:25:18.9215164</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Biosciences, Geography and Physics - Biosciences</level></path><authors><author><firstname>Charlotte</firstname><surname>Christensen</surname><order>1</order></author><author><firstname>Anna</firstname><surname>Bracken</surname><order>2</order></author><author><firstname>M. Justin</firstname><surname>O'Riain</surname><orcid>0000-0001-5233-8327</orcid><order>3</order></author><author><firstname>Gaëlle</firstname><surname>Fehlmann</surname><orcid>0000-0001-7981-5728</orcid><order>4</order></author><author><firstname>Mark</firstname><surname>Holton</surname><orcid>0000-0001-8834-3283</orcid><order>5</order></author><author><firstname>Phillip</firstname><surname>Hopkins</surname><orcid>0009-0005-6570-6236</orcid><order>6</order></author><author><firstname>Andrew</firstname><surname>King</surname><orcid>0000-0002-6870-9767</orcid><order>7</order></author><author><firstname>Ines</firstname><surname>Fuertbauer</surname><orcid>0000-0003-1404-6280</orcid><order>8</order></author></authors><documents><document><filename>62974__27038__f9c9dec303124fa894abcea0ed2fae98.pdf</filename><originalFilename>62974.VOR.pdf</originalFilename><uploaded>2023-04-13T15:24:30.7364011</uploaded><type>Output</type><contentLength>1115074</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>Distributed under the terms of a Creative Commons Attribution 4.0 License.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 62974 2023-03-17 Quantifying allo-grooming in wild chacma baboons (Papio ursinus) using tri-axial acceleration data and machine learning 707c5165eb55a87ab23bc5bb9a10826f Charlotte Christensen Charlotte Christensen true false cfca3b883779efc03ecf86352832b39f Anna Bracken Anna Bracken true false 0e1d89d0cc934a740dcd0a873aed178e 0000-0001-8834-3283 Mark Holton Mark Holton true false cdb0ce5ff78d21e34aac34445b4a4c57 0009-0005-6570-6236 Phillip Hopkins Phillip Hopkins true false cc115b4bc4672840f960acc1cb078642 0000-0002-6870-9767 Andrew King Andrew King true false f682ec95fa97c4fabb57dc098a9fdaaa 0000-0003-1404-6280 Ines Fuertbauer Ines Fuertbauer true false 2023-03-17 SBI Quantification of activity budgets is pivotal for understanding how animals respond to changes in their environment. Social grooming is a key activity that underpins various social processes with consequences for health and fitness. Traditional methods use direct (focal) observations to calculate grooming rates, providing systematic but sparse data. Accelerometers, in contrast, can quantify activity budgets continuously but have not been used to quantify social grooming. We test whether grooming can be accurately identified using machine learning (random forest model) trained on labelled acceleration data from wild chacma baboons (Papio ursinus). We successfully identified giving and receiving grooming with high precision (81% and 91%) and recall (87% and 79%). Giving grooming was associated with a distinct rhythmical signal along the surge axis. Receiving grooming had similar acceleration signals to resting, and thus was more difficult to assign. We applied our machine learning model to n = 680 collar data days from n = 12 baboons and found that grooming rates obtained from accelerometers were significantly and positively correlated with direct observation rates for giving but not receiving grooming. The ability to collect continuous grooming data in wild populations will allow researchers to re-examine and expand upon long-standing questions regarding the formation and function of grooming bonds. Journal Article Royal Society Open Science 10 4 The Royal Society 2054-5703 machine learning, tri-axial accelerometers, random forest models, allo-grooming, activity budgets, primates 1 4 2023 2023-04-01 10.1098/rsos.221103 http://dx.doi.org/10.1098/rsos.221103 COLLEGE NANME Biosciences COLLEGE CODE SBI Swansea University SU Library paid the OA fee (TA Institutional Deal) Swansea University, NRF Incentive Funding 2023-06-23T15:41:17.5261595 2023-03-17T09:25:18.9215164 Faculty of Science and Engineering School of Biosciences, Geography and Physics - Biosciences Charlotte Christensen 1 Anna Bracken 2 M. Justin O'Riain 0000-0001-5233-8327 3 Gaëlle Fehlmann 0000-0001-7981-5728 4 Mark Holton 0000-0001-8834-3283 5 Phillip Hopkins 0009-0005-6570-6236 6 Andrew King 0000-0002-6870-9767 7 Ines Fuertbauer 0000-0003-1404-6280 8 62974__27038__f9c9dec303124fa894abcea0ed2fae98.pdf 62974.VOR.pdf 2023-04-13T15:24:30.7364011 Output 1115074 application/pdf Version of Record true Distributed under the terms of a Creative Commons Attribution 4.0 License. true eng https://creativecommons.org/licenses/by/4.0/
title Quantifying allo-grooming in wild chacma baboons (Papio ursinus) using tri-axial acceleration data and machine learning
spellingShingle Quantifying allo-grooming in wild chacma baboons (Papio ursinus) using tri-axial acceleration data and machine learning
Charlotte Christensen
Anna Bracken
Mark Holton
Phillip Hopkins
Andrew King
Ines Fuertbauer
title_short Quantifying allo-grooming in wild chacma baboons (Papio ursinus) using tri-axial acceleration data and machine learning
title_full Quantifying allo-grooming in wild chacma baboons (Papio ursinus) using tri-axial acceleration data and machine learning
title_fullStr Quantifying allo-grooming in wild chacma baboons (Papio ursinus) using tri-axial acceleration data and machine learning
title_full_unstemmed Quantifying allo-grooming in wild chacma baboons (Papio ursinus) using tri-axial acceleration data and machine learning
title_sort Quantifying allo-grooming in wild chacma baboons (Papio ursinus) using tri-axial acceleration data and machine learning
author_id_str_mv 707c5165eb55a87ab23bc5bb9a10826f
cfca3b883779efc03ecf86352832b39f
0e1d89d0cc934a740dcd0a873aed178e
cdb0ce5ff78d21e34aac34445b4a4c57
cc115b4bc4672840f960acc1cb078642
f682ec95fa97c4fabb57dc098a9fdaaa
author_id_fullname_str_mv 707c5165eb55a87ab23bc5bb9a10826f_***_Charlotte Christensen
cfca3b883779efc03ecf86352832b39f_***_Anna Bracken
0e1d89d0cc934a740dcd0a873aed178e_***_Mark Holton
cdb0ce5ff78d21e34aac34445b4a4c57_***_Phillip Hopkins
cc115b4bc4672840f960acc1cb078642_***_Andrew King
f682ec95fa97c4fabb57dc098a9fdaaa_***_Ines Fuertbauer
author Charlotte Christensen
Anna Bracken
Mark Holton
Phillip Hopkins
Andrew King
Ines Fuertbauer
author2 Charlotte Christensen
Anna Bracken
M. Justin O'Riain
Gaëlle Fehlmann
Mark Holton
Phillip Hopkins
Andrew King
Ines Fuertbauer
format Journal article
container_title Royal Society Open Science
container_volume 10
container_issue 4
publishDate 2023
institution Swansea University
issn 2054-5703
doi_str_mv 10.1098/rsos.221103
publisher The Royal Society
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Biosciences, Geography and Physics - Biosciences{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Biosciences, Geography and Physics - Biosciences
url http://dx.doi.org/10.1098/rsos.221103
document_store_str 1
active_str 0
description Quantification of activity budgets is pivotal for understanding how animals respond to changes in their environment. Social grooming is a key activity that underpins various social processes with consequences for health and fitness. Traditional methods use direct (focal) observations to calculate grooming rates, providing systematic but sparse data. Accelerometers, in contrast, can quantify activity budgets continuously but have not been used to quantify social grooming. We test whether grooming can be accurately identified using machine learning (random forest model) trained on labelled acceleration data from wild chacma baboons (Papio ursinus). We successfully identified giving and receiving grooming with high precision (81% and 91%) and recall (87% and 79%). Giving grooming was associated with a distinct rhythmical signal along the surge axis. Receiving grooming had similar acceleration signals to resting, and thus was more difficult to assign. We applied our machine learning model to n = 680 collar data days from n = 12 baboons and found that grooming rates obtained from accelerometers were significantly and positively correlated with direct observation rates for giving but not receiving grooming. The ability to collect continuous grooming data in wild populations will allow researchers to re-examine and expand upon long-standing questions regarding the formation and function of grooming bonds.
published_date 2023-04-01T15:41:12Z
_version_ 1769504791857201152
score 11.016235

Similar Items