Cargando…

Clustering for Automated Exploratory Pattern Discovery in Animal Behavioral Data

Traditional methods of data analysis in animal behavior research are usually based on measuring behavior by manually coding a set of chosen behavioral parameters, which is naturally prone to human bias and error, and is also a tedious labor-intensive task. Machine learning techniques are increasingl...

Descripción completa

Detalles Bibliográficos
Autores principales: Menaker, Tom, Monteny, Joke, de Beeck, Lin Op, Zamansky, Anna
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9260587/
https://www.ncbi.nlm.nih.gov/pubmed/35812846
http://dx.doi.org/10.3389/fvets.2022.884437
_version_ 1784742071608803328
author Menaker, Tom
Monteny, Joke
de Beeck, Lin Op
Zamansky, Anna
author_facet Menaker, Tom
Monteny, Joke
de Beeck, Lin Op
Zamansky, Anna
author_sort Menaker, Tom
collection PubMed
description Traditional methods of data analysis in animal behavior research are usually based on measuring behavior by manually coding a set of chosen behavioral parameters, which is naturally prone to human bias and error, and is also a tedious labor-intensive task. Machine learning techniques are increasingly applied to support researchers in this field, mostly in a supervised manner: for tracking animals, detecting land marks or recognizing actions. Unsupervised methods are increasingly used, but are under-explored in the context of behavior studies and applied contexts such as behavioral testing of dogs. This study explores the potential of unsupervised approaches such as clustering for the automated discovery of patterns in data which have potential behavioral meaning. We aim to demonstrate that such patterns can be useful at exploratory stages of data analysis before forming specific hypotheses. To this end, we propose a concrete method for grouping video trials of behavioral testing of animal individuals into clusters using a set of potentially relevant features. Using an example of protocol for testing in a “Stranger Test”, we compare the discovered clusters against the C-BARQ owner-based questionnaire, which is commonly used for dog behavioral trait assessment, showing that our method separated well between dogs with higher C-BARQ scores for stranger fear, and those with lower scores. This demonstrates potential use of such clustering approach for exploration prior to hypothesis forming and testing in behavioral research.
format Online
Article
Text
id pubmed-9260587
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-92605872022-07-08 Clustering for Automated Exploratory Pattern Discovery in Animal Behavioral Data Menaker, Tom Monteny, Joke de Beeck, Lin Op Zamansky, Anna Front Vet Sci Veterinary Science Traditional methods of data analysis in animal behavior research are usually based on measuring behavior by manually coding a set of chosen behavioral parameters, which is naturally prone to human bias and error, and is also a tedious labor-intensive task. Machine learning techniques are increasingly applied to support researchers in this field, mostly in a supervised manner: for tracking animals, detecting land marks or recognizing actions. Unsupervised methods are increasingly used, but are under-explored in the context of behavior studies and applied contexts such as behavioral testing of dogs. This study explores the potential of unsupervised approaches such as clustering for the automated discovery of patterns in data which have potential behavioral meaning. We aim to demonstrate that such patterns can be useful at exploratory stages of data analysis before forming specific hypotheses. To this end, we propose a concrete method for grouping video trials of behavioral testing of animal individuals into clusters using a set of potentially relevant features. Using an example of protocol for testing in a “Stranger Test”, we compare the discovered clusters against the C-BARQ owner-based questionnaire, which is commonly used for dog behavioral trait assessment, showing that our method separated well between dogs with higher C-BARQ scores for stranger fear, and those with lower scores. This demonstrates potential use of such clustering approach for exploration prior to hypothesis forming and testing in behavioral research. Frontiers Media S.A. 2022-06-23 /pmc/articles/PMC9260587/ /pubmed/35812846 http://dx.doi.org/10.3389/fvets.2022.884437 Text en Copyright © 2022 Menaker, Monteny, de Beeck and Zamansky. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Veterinary Science
Menaker, Tom
Monteny, Joke
de Beeck, Lin Op
Zamansky, Anna
Clustering for Automated Exploratory Pattern Discovery in Animal Behavioral Data
title Clustering for Automated Exploratory Pattern Discovery in Animal Behavioral Data
title_full Clustering for Automated Exploratory Pattern Discovery in Animal Behavioral Data
title_fullStr Clustering for Automated Exploratory Pattern Discovery in Animal Behavioral Data
title_full_unstemmed Clustering for Automated Exploratory Pattern Discovery in Animal Behavioral Data
title_short Clustering for Automated Exploratory Pattern Discovery in Animal Behavioral Data
title_sort clustering for automated exploratory pattern discovery in animal behavioral data
topic Veterinary Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9260587/
https://www.ncbi.nlm.nih.gov/pubmed/35812846
http://dx.doi.org/10.3389/fvets.2022.884437
work_keys_str_mv AT menakertom clusteringforautomatedexploratorypatterndiscoveryinanimalbehavioraldata
AT montenyjoke clusteringforautomatedexploratorypatterndiscoveryinanimalbehavioraldata
AT debeecklinop clusteringforautomatedexploratorypatterndiscoveryinanimalbehavioraldata
AT zamanskyanna clusteringforautomatedexploratorypatterndiscoveryinanimalbehavioraldata