IMIS

Publications | Institutes | Persons | Datasets | Projects | Maps
[ report an error in this record ]basket (1): add | show Print this page

one publication added to basket [244292]
Optimizing acceleration-based ethograms: the use of variable-time versus fixed-time segmentation
Bom, R.A.; Bouten, W.; Piersma, T.; Oosterbeek, K.; van Gils, J.A. (2014). Optimizing acceleration-based ethograms: the use of variable-time versus fixed-time segmentation. Movement Ecology 2(6): 1-8. http://dx.doi.org/10.1186/2051-3933-2-6
In: Movement Ecology. BioMed Central: London. e-ISSN 2051-3933, more
Peer reviewed article  

Available in  Authors 

Keyword
    Dromas ardeola Paykull, 1805 [WoRMS]
Author keywords
    Behaviour classification; Change-point model; Crab plover; Dromas ardeola; Movement ethogram

Authors  Top 
  • Bom, R.A., more
  • Bouten, W.
  • Piersma, T., more
  • Oosterbeek, K.
  • van Gils, J.A., more

Abstract
    Animal-borne accelerometers measure body orientation and movement and can thus be used to classify animal behaviour. To univocally and automatically analyse the large volume of data generated, we need classification models. An important step in the process of classification is the segmentation of acceleration data, i.e. the assignment of the boundaries between different behavioural classes in a time series. So far, analysts have worked with fixed-time segments, but this may weaken the strength of the derived classification models because transitions of behaviour do not necessarily coincide with boundaries of the segments. Here we develop random forest automated supervised classification models either built on variable-time segments generated with a so-called ‘change-point model’, or on fixed-time segments, and compare for eight behavioural classes the classification performance. The approach makes use of acceleration data measured in eight free-ranging crab plovers Dromas ardeola.

All data in the Integrated Marine Information System (IMIS) is subject to the VLIZ privacy policy Top | Authors