Cargando…

Quantifying influence of human choice on the automated detection of Drosophila behavior by a supervised machine learning algorithm

Automated quantification of behavior is increasingly prevalent in neuroscience research. Human judgments can influence machine-learning-based behavior classification at multiple steps in the process, for both supervised and unsupervised approaches. Such steps include the design of the algorithm for...

Descripción completa

Detalles Bibliográficos
Autores principales: Leng, Xubo, Wohl, Margot, Ishii, Kenichi, Nayak, Pavan, Asahina, Kenta
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7743940/
https://www.ncbi.nlm.nih.gov/pubmed/33326445
http://dx.doi.org/10.1371/journal.pone.0241696
_version_ 1783624332496338944
author Leng, Xubo
Wohl, Margot
Ishii, Kenichi
Nayak, Pavan
Asahina, Kenta
author_facet Leng, Xubo
Wohl, Margot
Ishii, Kenichi
Nayak, Pavan
Asahina, Kenta
author_sort Leng, Xubo
collection PubMed
description Automated quantification of behavior is increasingly prevalent in neuroscience research. Human judgments can influence machine-learning-based behavior classification at multiple steps in the process, for both supervised and unsupervised approaches. Such steps include the design of the algorithm for machine learning, the methods used for animal tracking, the choice of training images, and the benchmarking of classification outcomes. However, how these design choices contribute to the interpretation of automated behavioral classifications has not been extensively characterized. Here, we quantify the effects of experimenter choices on the outputs of automated classifiers of Drosophila social behaviors. Drosophila behaviors contain a considerable degree of variability, which was reflected in the confidence levels associated with both human and computer classifications. We found that a diversity of sex combinations and tracking features was important for robust performance of the automated classifiers. In particular, features concerning the relative position of flies contained useful information for training a machine-learning algorithm. These observations shed light on the importance of human influence on tracking algorithms, the selection of training images, and the quality of annotated sample images used to benchmark the performance of a classifier (the ‘ground truth’). Evaluation of these factors is necessary for researchers to accurately interpret behavioral data quantified by a machine-learning algorithm and to further improve automated classifications.
format Online
Article
Text
id pubmed-7743940
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-77439402020-12-31 Quantifying influence of human choice on the automated detection of Drosophila behavior by a supervised machine learning algorithm Leng, Xubo Wohl, Margot Ishii, Kenichi Nayak, Pavan Asahina, Kenta PLoS One Research Article Automated quantification of behavior is increasingly prevalent in neuroscience research. Human judgments can influence machine-learning-based behavior classification at multiple steps in the process, for both supervised and unsupervised approaches. Such steps include the design of the algorithm for machine learning, the methods used for animal tracking, the choice of training images, and the benchmarking of classification outcomes. However, how these design choices contribute to the interpretation of automated behavioral classifications has not been extensively characterized. Here, we quantify the effects of experimenter choices on the outputs of automated classifiers of Drosophila social behaviors. Drosophila behaviors contain a considerable degree of variability, which was reflected in the confidence levels associated with both human and computer classifications. We found that a diversity of sex combinations and tracking features was important for robust performance of the automated classifiers. In particular, features concerning the relative position of flies contained useful information for training a machine-learning algorithm. These observations shed light on the importance of human influence on tracking algorithms, the selection of training images, and the quality of annotated sample images used to benchmark the performance of a classifier (the ‘ground truth’). Evaluation of these factors is necessary for researchers to accurately interpret behavioral data quantified by a machine-learning algorithm and to further improve automated classifications. Public Library of Science 2020-12-16 /pmc/articles/PMC7743940/ /pubmed/33326445 http://dx.doi.org/10.1371/journal.pone.0241696 Text en © 2020 Leng et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Leng, Xubo
Wohl, Margot
Ishii, Kenichi
Nayak, Pavan
Asahina, Kenta
Quantifying influence of human choice on the automated detection of Drosophila behavior by a supervised machine learning algorithm
title Quantifying influence of human choice on the automated detection of Drosophila behavior by a supervised machine learning algorithm
title_full Quantifying influence of human choice on the automated detection of Drosophila behavior by a supervised machine learning algorithm
title_fullStr Quantifying influence of human choice on the automated detection of Drosophila behavior by a supervised machine learning algorithm
title_full_unstemmed Quantifying influence of human choice on the automated detection of Drosophila behavior by a supervised machine learning algorithm
title_short Quantifying influence of human choice on the automated detection of Drosophila behavior by a supervised machine learning algorithm
title_sort quantifying influence of human choice on the automated detection of drosophila behavior by a supervised machine learning algorithm
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7743940/
https://www.ncbi.nlm.nih.gov/pubmed/33326445
http://dx.doi.org/10.1371/journal.pone.0241696
work_keys_str_mv AT lengxubo quantifyinginfluenceofhumanchoiceontheautomateddetectionofdrosophilabehaviorbyasupervisedmachinelearningalgorithm
AT wohlmargot quantifyinginfluenceofhumanchoiceontheautomateddetectionofdrosophilabehaviorbyasupervisedmachinelearningalgorithm
AT ishiikenichi quantifyinginfluenceofhumanchoiceontheautomateddetectionofdrosophilabehaviorbyasupervisedmachinelearningalgorithm
AT nayakpavan quantifyinginfluenceofhumanchoiceontheautomateddetectionofdrosophilabehaviorbyasupervisedmachinelearningalgorithm
AT asahinakenta quantifyinginfluenceofhumanchoiceontheautomateddetectionofdrosophilabehaviorbyasupervisedmachinelearningalgorithm