The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data
Abstract The recent increase in data accuracy from high resolution accelerometers offers substantial potential for improved understanding and prediction of animal movements. However, current approaches used for analysing these multivariable datasets typically require existing knowledge of the behavi...
id |
fttriple:oai:gotriple.eu:50|dedup_wf_001::08c301545a815bc2e29b6ac6d14d1ce4 |
---|---|
record_format |
openpolar |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
fttriple |
language |
English |
topic |
Original Research Accelerometer data animal movements behavioral classification unsupervised learning Ecology Evolution Behavior and Systematics Nature and Landscape Conservation info envir |
spellingShingle |
Original Research Accelerometer data animal movements behavioral classification unsupervised learning Ecology Evolution Behavior and Systematics Nature and Landscape Conservation info envir Thomas Cornulier Ian M. Davies Beth E. Scott Marianna Chimienti Ellie Owen Justin M. J. Travis Mark Bolton The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data |
topic_facet |
Original Research Accelerometer data animal movements behavioral classification unsupervised learning Ecology Evolution Behavior and Systematics Nature and Landscape Conservation info envir |
description |
Abstract The recent increase in data accuracy from high resolution accelerometers offers substantial potential for improved understanding and prediction of animal movements. However, current approaches used for analysing these multivariable datasets typically require existing knowledge of the behaviors of the animals to inform the behavioral classification process. These methods are thus not well‐suited for the many cases where limited knowledge of the different behaviors performed exist. Here, we introduce the use of an unsupervised learning algorithm. To illustrate the method's capability we analyse data collected using a combination of GPS and Accelerometers on two seabird species: razorbills (Alca torda) and common guillemots (Uria aalge). We applied the unsupervised learning algorithm Expectation Maximization to characterize latent behavioral states both above and below water at both individual and group level. The application of this flexible approach yielded significant new insights into the foraging strategies of the two study species, both above and below the surface of the water. In addition to general behavioral modes such as flying, floating, as well as descending and ascending phases within the water column, this approach allowed an exploration of previously unstudied and important behaviors such as searching and prey chasing/capture events. We propose that this unsupervised learning approach provides an ideal tool for the systematic analysis of such complex multivariable movement data that are increasingly being obtained with accelerometer tags across species. In particular, we recommend its application in cases where we have limited current knowledge of the behaviors performed and existing supervised learning approaches may have limited utility. |
format |
Article in Journal/Newspaper |
author |
Thomas Cornulier Ian M. Davies Beth E. Scott Marianna Chimienti Ellie Owen Justin M. J. Travis Mark Bolton |
author_facet |
Thomas Cornulier Ian M. Davies Beth E. Scott Marianna Chimienti Ellie Owen Justin M. J. Travis Mark Bolton |
author_sort |
Thomas Cornulier |
title |
The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data |
title_short |
The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data |
title_full |
The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data |
title_fullStr |
The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data |
title_full_unstemmed |
The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data |
title_sort |
use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data |
publisher |
John Wiley and Sons Inc. |
publishDate |
2016 |
url |
http://aura.abdn.ac.uk/bitstream/2164/5503/1/Chimienti_et_al_2016_Ecology_and_Evolution.pdf http://europepmc.org/articles/PMC4739568 https://doi.org/10.1002/ece3.1914 https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1002%2Fece3.1914 http://onlinelibrary.wiley.com/wol1/doi/10.1002/ece3.1914/fullpdf https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/ece3.1914 https://onlinelibrary.wiley.com/doi/full/10.1002/ece3.1914 https://onlinelibrary.wiley.com/doi/pdf/10.1002/ece3.1914 https://www.ncbi.nlm.nih.gov/pubmed/26865961 http://europepmc.org/abstract/MED/26865961 https://core.ac.uk/display/77050512 http://onlinelibrary.wiley.com/doi/10.1002/ece3.1914/full https://abdn.pure.elsevier.com/en/publications/the-use-of-an-unsupervised-learning-approach-for-characterizing-l http://aura-test.abdn.ac.uk/handle/2164/5503 https://aura.abdn.ac.uk/handle/2164/5503?show=full https://academic.microsoft.com/#/detail/2255128034 |
genre |
Alca torda Uria aalge uria |
genre_facet |
Alca torda Uria aalge uria |
op_source |
oai:pubmedcentral.nih.gov:4739568 26865961 10.1002/ece3.1914 2255128034 10|opendoar____::eda80a3d5b344bc40f3bc04f65b7a357 10|opendoar____::8b6dd7db9af49e67306feb59a8bdc52c 10|openaire____::55045bd2a65019fd8e6741a755395c8c 10|openaire____::9e3be59865b2c1c335d32dae2fe7b254 10|openaire____::081b82f96300b6a6e3d282bad31cb6e2 10|doajarticles::13ae4a9d2a75f5bb322f19d8ef599c7c 10|openaire____::8ac8380272269217cb09a928c8caa993 10|openaire____::5f532a3fc4f1ea403f37070f59a7a53a 10|openaire____::806360c771262b4d6770e7cdf04b5c5a |
op_relation |
http://aura.abdn.ac.uk/bitstream/2164/5503/1/Chimienti_et_al_2016_Ecology_and_Evolution.pdf http://europepmc.org/articles/PMC4739568 https://dx.doi.org/10.1002/ece3.1914 http://dx.doi.org/10.1002/ece3.1914 https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1002%2Fece3.1914 http://onlinelibrary.wiley.com/wol1/doi/10.1002/ece3.1914/fullpdf https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/ece3.1914 https://onlinelibrary.wiley.com/doi/full/10.1002/ece3.1914 https://onlinelibrary.wiley.com/doi/pdf/10.1002/ece3.1914 https://www.ncbi.nlm.nih.gov/pubmed/26865961 http://europepmc.org/abstract/MED/26865961 https://core.ac.uk/display/77050512 http://onlinelibrary.wiley.com/doi/10.1002/ece3.1914/full https://abdn.pure.elsevier.com/en/publications/the-use-of-an-unsupervised-learning-approach-for-characterizing-l http://aura-test.abdn.ac.uk/handle/2164/5503 https://aura.abdn.ac.uk/handle/2164/5503?show=full https://academic.microsoft.com/#/detail/2255128034 |
op_rights |
lic_creative-commons |
op_doi |
https://doi.org/10.1002/ece3.1914 |
container_title |
Ecology and Evolution |
container_volume |
6 |
container_issue |
3 |
container_start_page |
727 |
op_container_end_page |
741 |
_version_ |
1766251345354948608 |
spelling |
fttriple:oai:gotriple.eu:50|dedup_wf_001::08c301545a815bc2e29b6ac6d14d1ce4 2023-05-15T13:12:19+02:00 The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data Thomas Cornulier Ian M. Davies Beth E. Scott Marianna Chimienti Ellie Owen Justin M. J. Travis Mark Bolton 2016-01-11 http://aura.abdn.ac.uk/bitstream/2164/5503/1/Chimienti_et_al_2016_Ecology_and_Evolution.pdf http://europepmc.org/articles/PMC4739568 https://doi.org/10.1002/ece3.1914 https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1002%2Fece3.1914 http://onlinelibrary.wiley.com/wol1/doi/10.1002/ece3.1914/fullpdf https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/ece3.1914 https://onlinelibrary.wiley.com/doi/full/10.1002/ece3.1914 https://onlinelibrary.wiley.com/doi/pdf/10.1002/ece3.1914 https://www.ncbi.nlm.nih.gov/pubmed/26865961 http://europepmc.org/abstract/MED/26865961 https://core.ac.uk/display/77050512 http://onlinelibrary.wiley.com/doi/10.1002/ece3.1914/full https://abdn.pure.elsevier.com/en/publications/the-use-of-an-unsupervised-learning-approach-for-characterizing-l http://aura-test.abdn.ac.uk/handle/2164/5503 https://aura.abdn.ac.uk/handle/2164/5503?show=full https://academic.microsoft.com/#/detail/2255128034 en eng John Wiley and Sons Inc. http://aura.abdn.ac.uk/bitstream/2164/5503/1/Chimienti_et_al_2016_Ecology_and_Evolution.pdf http://europepmc.org/articles/PMC4739568 https://dx.doi.org/10.1002/ece3.1914 http://dx.doi.org/10.1002/ece3.1914 https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1002%2Fece3.1914 http://onlinelibrary.wiley.com/wol1/doi/10.1002/ece3.1914/fullpdf https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/ece3.1914 https://onlinelibrary.wiley.com/doi/full/10.1002/ece3.1914 https://onlinelibrary.wiley.com/doi/pdf/10.1002/ece3.1914 https://www.ncbi.nlm.nih.gov/pubmed/26865961 http://europepmc.org/abstract/MED/26865961 https://core.ac.uk/display/77050512 http://onlinelibrary.wiley.com/doi/10.1002/ece3.1914/full https://abdn.pure.elsevier.com/en/publications/the-use-of-an-unsupervised-learning-approach-for-characterizing-l http://aura-test.abdn.ac.uk/handle/2164/5503 https://aura.abdn.ac.uk/handle/2164/5503?show=full https://academic.microsoft.com/#/detail/2255128034 lic_creative-commons oai:pubmedcentral.nih.gov:4739568 26865961 10.1002/ece3.1914 2255128034 10|opendoar____::eda80a3d5b344bc40f3bc04f65b7a357 10|opendoar____::8b6dd7db9af49e67306feb59a8bdc52c 10|openaire____::55045bd2a65019fd8e6741a755395c8c 10|openaire____::9e3be59865b2c1c335d32dae2fe7b254 10|openaire____::081b82f96300b6a6e3d282bad31cb6e2 10|doajarticles::13ae4a9d2a75f5bb322f19d8ef599c7c 10|openaire____::8ac8380272269217cb09a928c8caa993 10|openaire____::5f532a3fc4f1ea403f37070f59a7a53a 10|openaire____::806360c771262b4d6770e7cdf04b5c5a Original Research Accelerometer data animal movements behavioral classification unsupervised learning Ecology Evolution Behavior and Systematics Nature and Landscape Conservation info envir Journal Article https://vocabularies.coar-repositories.org/resource_types/c_6501/ 2016 fttriple https://doi.org/10.1002/ece3.1914 2023-01-22T17:23:15Z Abstract The recent increase in data accuracy from high resolution accelerometers offers substantial potential for improved understanding and prediction of animal movements. However, current approaches used for analysing these multivariable datasets typically require existing knowledge of the behaviors of the animals to inform the behavioral classification process. These methods are thus not well‐suited for the many cases where limited knowledge of the different behaviors performed exist. Here, we introduce the use of an unsupervised learning algorithm. To illustrate the method's capability we analyse data collected using a combination of GPS and Accelerometers on two seabird species: razorbills (Alca torda) and common guillemots (Uria aalge). We applied the unsupervised learning algorithm Expectation Maximization to characterize latent behavioral states both above and below water at both individual and group level. The application of this flexible approach yielded significant new insights into the foraging strategies of the two study species, both above and below the surface of the water. In addition to general behavioral modes such as flying, floating, as well as descending and ascending phases within the water column, this approach allowed an exploration of previously unstudied and important behaviors such as searching and prey chasing/capture events. We propose that this unsupervised learning approach provides an ideal tool for the systematic analysis of such complex multivariable movement data that are increasingly being obtained with accelerometer tags across species. In particular, we recommend its application in cases where we have limited current knowledge of the behaviors performed and existing supervised learning approaches may have limited utility. Article in Journal/Newspaper Alca torda Uria aalge uria Unknown Ecology and Evolution 6 3 727 741 |