Repository logo
 

Correcting a bias in the computation of behavioural time budgets that are based on supervised learning

Simple item page
cam.issuedOnline2022-04-25
dc.contributor.authorResheff, Yehezkel S
dc.contributor.authorBensch, Hanna M
dc.contributor.authorZöttl, Markus
dc.contributor.authorRotics, Shay
dc.contributor.orcidResheff, Yehezkel S [0000-0001-7863-7632]
dc.contributor.orcidBensch, Hanna M [0000-0002-8449-9843]
dc.contributor.orcidRotics, Shay [0000-0002-3858-1811]
dc.date.accessioned2022-04-26T08:00:28Z
dc.date.available2022-04-26T08:00:28Z
dc.date.issued2022-07
dc.date.submitted2021-12-10
dc.date.updated2022-04-26T08:00:28Z
dc.description.abstract<jats:title>Abstract</jats:title><jats:p> <jats:list> <jats:list-item><jats:p>Supervised learning of behavioural modes from body acceleration data has become a widely used research tool in Behavioural Ecology over the past decade. One of the primary usages of this tool is to estimate behavioural time budgets from the distribution of behaviours as predicted by the model. These serve as the key parameters to test predictions about the variation in animal behaviour. In this paper we show that the widespread computation of behavioural time budgets is biased, due to ignoring the classification model confusion probabilities.</jats:p></jats:list-item> <jats:list-item><jats:p>Next, we introduce <jats:italic>the confusion matrix correction for time budgets</jats:italic>—a simple correction method for adjusting the computed time budgets based on the model's confusion matrix.</jats:p></jats:list-item> <jats:list-item><jats:p>Finally, we show that the proposed correction is able to eliminate the bias, both theoretically and empirically in a series of data simulations on body acceleration data of a fossorial rodent species (Damaraland mole‐rat <jats:italic>Fukomys damarensis</jats:italic>).</jats:p></jats:list-item> <jats:list-item><jats:p>Our paper provides a simple implementation of <jats:italic>the confusion matrix correction for time budgets</jats:italic>, and we encourage researchers to use it to improve accuracy of behavioural time budget calculations.</jats:p></jats:list-item> </jats:list> </jats:p>
dc.identifier.doi10.17863/CAM.83869
dc.identifier.eissn2041-210X
dc.identifier.issn2041-210X
dc.identifier.othermee313862
dc.identifier.othermee-21-12-955.r2
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/336451
dc.languageen
dc.language.isoeng
dc.publisherWiley
dc.publisher.urlhttp://dx.doi.org/10.1111/2041-210x.13862
dc.subjectBehavioural ecology
dc.subjectMovement ecology
dc.subjectZoology
dc.subjectRESEARCH ARTICLE
dc.subjectRESEARCH ARTICLES
dc.subjectanimal behaviour
dc.subjectbehavioural time budget
dc.subjectbiologging
dc.subjectbiotelemetry
dc.subjectbody acceleration
dc.subjectmachine learning
dc.titleCorrecting a bias in the computation of behavioural time budgets that are based on supervised learning
dc.typeArticle
dcterms.dateAccepted2022-02-21
prism.publicationNameMethods in Ecology and Evolution
pubs.funder-project-idCrafoordska Stiftelsen (2018‐2259 2020‐ 0976)
pubs.funder-project-idHorizon 2020 Framework Programme (742808)
rioxxterms.licenseref.urihttp://creativecommons.org/licenses/by-nc/4.0/
rioxxterms.versionVoR
rioxxterms.versionofrecord10.1111/2041-210x.13862

Files

Original bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
2041-210X.13862.xml
Size:
8.56 KB
Format:
Extensible Markup Language
Description:
Bibliographic metadata
Licence
http://creativecommons.org/licenses/by-nc/4.0/
Download
Thumbnail Image
Name:
2041-210X.13862.pdf
Size:
4.66 MB
Format:
Adobe Portable Document Format
Description:
Published version
Licence
http://creativecommons.org/licenses/by-nc/4.0/
Download

Collections

Jisc Publications Router