The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data

Marianna Chimienti, Thomas Cornulier, Ellie Owen, Mark Bolton, Ian M. Davies, Justin M. J. Travis, Beth E. Scott

Research output: Contribution to journalArticlepeer-review

45 Citations (Scopus)
9 Downloads (Pure)


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 wellsuited 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.
Original languageEnglish
Pages (from-to)727–741
Number of pages15
JournalEcology and Evolution
Issue number3
Early online date11 Jan 2016
Publication statusPublished - Feb 2016

Bibliographical note


This project and the tags deployed on both seabird's species were fund by NERC (grant number NE/K007440/1), Marine Scotland Science and Seabird Tracking and Research (STAR) Project led by the Royal Society for the Protection of Birds (RSPB). We would like to thank Rob Hughes, Tessa Cole and Ruth Brown for helping in the data collection, the Bird Observatory of Fair Isle for supporting the fieldwork and the Marine Collaboration Research Forum (MarCRF).


  • Accelerometer data
  • animal movements
  • behavioral classification
  • unsupervised learning


Dive into the research topics of 'The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data'. Together they form a unique fingerprint.

Cite this