Data from: The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data
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 th...
Main Authors: | , , , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
2016
|
Subjects: | |
Online Access: | http://hdl.handle.net/10255/dryad.105878 https://doi.org/10.5061/dryad.5rg72 |
id |
ftdryad:oai:v1.datadryad.org:10255/dryad.105878 |
---|---|
record_format |
openpolar |
spelling |
ftdryad:oai:v1.datadryad.org:10255/dryad.105878 2023-05-15T13:12:18+02:00 Data from: The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data Chimienti, Marianna Cornulier, Thomas Owen, Ellie Bolton, Mark Davies, Ian M. Travis, Justin M. J. Scott, Beth E. 2016-01-13T19:31:05Z http://hdl.handle.net/10255/dryad.105878 https://doi.org/10.5061/dryad.5rg72 unknown doi:10.5061/dryad.5rg72/1 doi:10.5061/dryad.5rg72/2 doi:10.1002/ece3.1914 PMID:26865961 doi:10.5061/dryad.5rg72 Chimienti M, Cornulier T, Owen E, Bolton M, Davies IM, Travis JMJ, Scott BE (2016) The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data. Ecology and Evolution 6(3): 727–741. http://hdl.handle.net/10255/dryad.105878 Article 2016 ftdryad https://doi.org/10.5061/dryad.5rg72 https://doi.org/10.5061/dryad.5rg72/1 https://doi.org/10.5061/dryad.5rg72/2 https://doi.org/10.1002/ece3.1914 2020-01-01T15:29:09Z 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 Dryad Digital Repository (Duke University) |
institution |
Open Polar |
collection |
Dryad Digital Repository (Duke University) |
op_collection_id |
ftdryad |
language |
unknown |
description |
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 |
Chimienti, Marianna Cornulier, Thomas Owen, Ellie Bolton, Mark Davies, Ian M. Travis, Justin M. J. Scott, Beth E. |
spellingShingle |
Chimienti, Marianna Cornulier, Thomas Owen, Ellie Bolton, Mark Davies, Ian M. Travis, Justin M. J. Scott, Beth E. Data from: The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data |
author_facet |
Chimienti, Marianna Cornulier, Thomas Owen, Ellie Bolton, Mark Davies, Ian M. Travis, Justin M. J. Scott, Beth E. |
author_sort |
Chimienti, Marianna |
title |
Data from: The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data |
title_short |
Data from: The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data |
title_full |
Data from: The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data |
title_fullStr |
Data from: The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data |
title_full_unstemmed |
Data from: The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data |
title_sort |
data from: the use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data |
publishDate |
2016 |
url |
http://hdl.handle.net/10255/dryad.105878 https://doi.org/10.5061/dryad.5rg72 |
genre |
Alca torda Uria aalge uria |
genre_facet |
Alca torda Uria aalge uria |
op_relation |
doi:10.5061/dryad.5rg72/1 doi:10.5061/dryad.5rg72/2 doi:10.1002/ece3.1914 PMID:26865961 doi:10.5061/dryad.5rg72 Chimienti M, Cornulier T, Owen E, Bolton M, Davies IM, Travis JMJ, Scott BE (2016) The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data. Ecology and Evolution 6(3): 727–741. http://hdl.handle.net/10255/dryad.105878 |
op_doi |
https://doi.org/10.5061/dryad.5rg72 https://doi.org/10.5061/dryad.5rg72/1 https://doi.org/10.5061/dryad.5rg72/2 https://doi.org/10.1002/ece3.1914 |
_version_ |
1766251236455088128 |