A comparison of techniques for classifying behavior from accelerometers for two species of seabird
Abstract The behavior of many wild animals remains a mystery, as it is difficult to quantify behavior of species that cannot be easily followed throughout their daily or seasonal movements. Accelerometers can solve some of these mysteries, as they collect activity data at a high temporal resolution...
Published in: | Ecology and Evolution |
---|---|
Main Authors: | , , , , |
Other Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Wiley
2019
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1002/ece3.4740 https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1002%2Fece3.4740 https://onlinelibrary.wiley.com/doi/pdf/10.1002/ece3.4740 https://onlinelibrary.wiley.com/doi/full-xml/10.1002/ece3.4740 |
id |
crwiley:10.1002/ece3.4740 |
---|---|
record_format |
openpolar |
spelling |
crwiley:10.1002/ece3.4740 2024-06-23T07:56:27+00:00 A comparison of techniques for classifying behavior from accelerometers for two species of seabird Patterson, Allison Gilchrist, Hugh Grant Chivers, Lorraine Hatch, Scott Elliott, Kyle British Ornithologists’ Union Natural Sciences and Engineering Research Council of Canada McGill University University of Manitoba 2019 http://dx.doi.org/10.1002/ece3.4740 https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1002%2Fece3.4740 https://onlinelibrary.wiley.com/doi/pdf/10.1002/ece3.4740 https://onlinelibrary.wiley.com/doi/full-xml/10.1002/ece3.4740 en eng Wiley http://creativecommons.org/licenses/by/4.0/ Ecology and Evolution volume 9, issue 6, page 3030-3045 ISSN 2045-7758 2045-7758 journal-article 2019 crwiley https://doi.org/10.1002/ece3.4740 2024-06-11T04:43:09Z Abstract The behavior of many wild animals remains a mystery, as it is difficult to quantify behavior of species that cannot be easily followed throughout their daily or seasonal movements. Accelerometers can solve some of these mysteries, as they collect activity data at a high temporal resolution (<1 s), can be relatively small (<1 g) so they minimally disrupt behavior, and are increasingly capable of recording data for long periods. Nonetheless, there is a need for increased validation of methods to classify animal behavior from accelerometers to promote widespread adoption of this technology in ecology. We assessed the accuracy of six different behavioral assignment methods for two species of seabird, thick‐billed murres ( Uria lomvia ) and black‐legged kittiwakes ( Rissa tridactyla ). We identified three behaviors using tri‐axial accelerometers: standing, swimming, and flying, after classifying diving using a pressure sensor for murres. We evaluated six classification methods relative to independent classifications from concurrent GPS tracking data. We used four variables for classification: depth, wing beat frequency, pitch, and dynamic acceleration. Average accuracy for all methods was >98% for murres, and 89% and 93% for kittiwakes during incubation and chick rearing, respectively. Variable selection showed that classification accuracy did not improve with more than two (kittiwakes) or three (murres) variables. We conclude that simple methods of behavioral classification can be as accurate for classifying basic behaviors as more complex approaches, and that identifying suitable accelerometer metrics is more important than using a particular classification method when the objective is to develop a daily activity or energy budget. Highly accurate daily activity budgets can be generated from accelerometer data using multiple methods and a small number of accelerometer metrics; therefore, identifying a suitable behavioral classification method should not be a barrier to using accelerometers in ... Article in Journal/Newspaper rissa tridactyla Uria lomvia uria Wiley Online Library Ecology and Evolution 9 6 3030 3045 |
institution |
Open Polar |
collection |
Wiley Online Library |
op_collection_id |
crwiley |
language |
English |
description |
Abstract The behavior of many wild animals remains a mystery, as it is difficult to quantify behavior of species that cannot be easily followed throughout their daily or seasonal movements. Accelerometers can solve some of these mysteries, as they collect activity data at a high temporal resolution (<1 s), can be relatively small (<1 g) so they minimally disrupt behavior, and are increasingly capable of recording data for long periods. Nonetheless, there is a need for increased validation of methods to classify animal behavior from accelerometers to promote widespread adoption of this technology in ecology. We assessed the accuracy of six different behavioral assignment methods for two species of seabird, thick‐billed murres ( Uria lomvia ) and black‐legged kittiwakes ( Rissa tridactyla ). We identified three behaviors using tri‐axial accelerometers: standing, swimming, and flying, after classifying diving using a pressure sensor for murres. We evaluated six classification methods relative to independent classifications from concurrent GPS tracking data. We used four variables for classification: depth, wing beat frequency, pitch, and dynamic acceleration. Average accuracy for all methods was >98% for murres, and 89% and 93% for kittiwakes during incubation and chick rearing, respectively. Variable selection showed that classification accuracy did not improve with more than two (kittiwakes) or three (murres) variables. We conclude that simple methods of behavioral classification can be as accurate for classifying basic behaviors as more complex approaches, and that identifying suitable accelerometer metrics is more important than using a particular classification method when the objective is to develop a daily activity or energy budget. Highly accurate daily activity budgets can be generated from accelerometer data using multiple methods and a small number of accelerometer metrics; therefore, identifying a suitable behavioral classification method should not be a barrier to using accelerometers in ... |
author2 |
British Ornithologists’ Union Natural Sciences and Engineering Research Council of Canada McGill University University of Manitoba |
format |
Article in Journal/Newspaper |
author |
Patterson, Allison Gilchrist, Hugh Grant Chivers, Lorraine Hatch, Scott Elliott, Kyle |
spellingShingle |
Patterson, Allison Gilchrist, Hugh Grant Chivers, Lorraine Hatch, Scott Elliott, Kyle A comparison of techniques for classifying behavior from accelerometers for two species of seabird |
author_facet |
Patterson, Allison Gilchrist, Hugh Grant Chivers, Lorraine Hatch, Scott Elliott, Kyle |
author_sort |
Patterson, Allison |
title |
A comparison of techniques for classifying behavior from accelerometers for two species of seabird |
title_short |
A comparison of techniques for classifying behavior from accelerometers for two species of seabird |
title_full |
A comparison of techniques for classifying behavior from accelerometers for two species of seabird |
title_fullStr |
A comparison of techniques for classifying behavior from accelerometers for two species of seabird |
title_full_unstemmed |
A comparison of techniques for classifying behavior from accelerometers for two species of seabird |
title_sort |
comparison of techniques for classifying behavior from accelerometers for two species of seabird |
publisher |
Wiley |
publishDate |
2019 |
url |
http://dx.doi.org/10.1002/ece3.4740 https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1002%2Fece3.4740 https://onlinelibrary.wiley.com/doi/pdf/10.1002/ece3.4740 https://onlinelibrary.wiley.com/doi/full-xml/10.1002/ece3.4740 |
genre |
rissa tridactyla Uria lomvia uria |
genre_facet |
rissa tridactyla Uria lomvia uria |
op_source |
Ecology and Evolution volume 9, issue 6, page 3030-3045 ISSN 2045-7758 2045-7758 |
op_rights |
http://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.1002/ece3.4740 |
container_title |
Ecology and Evolution |
container_volume |
9 |
container_issue |
6 |
container_start_page |
3030 |
op_container_end_page |
3045 |
_version_ |
1802649534110629888 |