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

Change log
Resheff, Yehezkel S  ORCID logo
Zöttl, Markus 

jats:titleAbstract</jats:title>jats:p jats:list

jats:list-itemjats:pSupervised 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-itemjats:pNext, we introduce jats:italicthe 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-itemjats:pFinally, 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:italicFukomys damarensis</jats:italic>).</jats:p></jats:list-item>

jats:list-itemjats:pOur paper provides a simple implementation of jats:italicthe 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>

Behavioural ecology, Movement ecology, Zoology, RESEARCH ARTICLE, RESEARCH ARTICLES, animal behaviour, behavioural time budget, biologging, biotelemetry, body acceleration, machine learning
Journal Title
Methods in Ecology and Evolution
Conference Name
Journal ISSN
Volume Title
Crafoordska Stiftelsen (2018‐2259 2020‐ 0976)
Horizon 2020 Framework Programme (742808)