Title |
Optimizing acceleration-based ethograms: the use of variable-time versus fixed-time segmentation
|
---|---|
Published in |
Movement Ecology, March 2014
|
DOI | 10.1186/2051-3933-2-6 |
Pubmed ID | |
Authors |
Roeland A Bom, Willem Bouten, Theunis Piersma, Kees Oosterbeek, Jan A van Gils |
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. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
Netherlands | 1 | 33% |
United Kingdom | 1 | 33% |
Unknown | 1 | 33% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Members of the public | 3 | 100% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
United Kingdom | 1 | <1% |
Denmark | 1 | <1% |
Unknown | 152 | 99% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 35 | 23% |
Student > Master | 27 | 18% |
Researcher | 26 | 17% |
Student > Bachelor | 18 | 12% |
Student > Doctoral Student | 7 | 5% |
Other | 18 | 12% |
Unknown | 23 | 15% |
Readers by discipline | Count | As % |
---|---|---|
Agricultural and Biological Sciences | 78 | 51% |
Environmental Science | 23 | 15% |
Computer Science | 4 | 3% |
Earth and Planetary Sciences | 4 | 3% |
Neuroscience | 3 | 2% |
Other | 8 | 5% |
Unknown | 34 | 22% |