Openly accessible

An evaluation of machine learning classifiers for next-generation, continuous-ethogram smart trackers

Yu, Hui, Deng, Jian, Nathan, Ran, Kröschel, Max, Pekarsky, Sasha, Li, Guozheng and Klaassen, Marcel 2021, An evaluation of machine learning classifiers for next-generation, continuous-ethogram smart trackers, Movement ecology, vol. 9, no. 1, pp. 1-14, doi: 10.1186/s40462-021-00245-x.

Attached Files
Name Description MIMEType Size Downloads

Title An evaluation of machine learning classifiers for next-generation, continuous-ethogram smart trackers
Author(s) Yu, Hui
Deng, Jian
Nathan, Ran
Kröschel, Max
Pekarsky, Sasha
Li, Guozheng
Klaassen, MarcelORCID iD for Klaassen, Marcel orcid.org/0000-0003-3907-9599
Journal name Movement ecology
Volume number 9
Issue number 1
Article ID 15
Start page 1
End page 14
Total pages 14
Publisher BioMed Central
Place of publication London, Eng.
Publication date 2021-12
ISSN 2051-3933
2051-3933
Keyword(s) ANN
Accelerometer
Behaviour classification
On-board processing
Random forest
XGBoost
Summary Background Our understanding of movement patterns and behaviours of wildlife has advanced greatly through the use of improved tracking technologies, including application of accelerometry (ACC) across a wide range of taxa. However, most ACC studies either use intermittent sampling that hinders continuity or continuous data logging relying on tracker retrieval for data downloading which is not applicable for long term study. To allow long-term, fine-scale behavioural research, we evaluated a range of machine learning methods for their suitability for continuous on-board classification of ACC data into behaviour categories prior to data transmission. Methods We tested six supervised machine learning methods, including linear discriminant analysis (LDA), decision tree (DT), support vector machine (SVM), artificial neural network (ANN), random forest (RF) and extreme gradient boosting (XGBoost) to classify behaviour using ACC data from three bird species (white stork Ciconia ciconia, griffon vulture Gyps fulvus and common crane Grus grus) and two mammals (dairy cow Bos taurus and roe deer Capreolus capreolus). Results Using a range of quality criteria, SVM, ANN, RF and XGBoost performed well in determining behaviour from ACC data and their good performance appeared little affected when greatly reducing the number of input features for model training. On-board runtime and storage-requirement tests showed that notably ANN, RF and XGBoost would make suitable on-board classifiers. Conclusions Our identification of using feature reduction in combination with ANN, RF and XGBoost as suitable methods for on-board behavioural classification of continuous ACC data has considerable potential to benefit movement ecology and behavioural research, wildlife conservation and livestock husbandry.
Language eng
DOI 10.1186/s40462-021-00245-x
Indigenous content off
Field of Research 0502 Environmental Science and Management
0602 Ecology
HERDC Research category C1 Refereed article in a scholarly journal
ERA Research output type C Journal article
Free to Read? Yes
Persistent URL http://hdl.handle.net/10536/DRO/DU:30150016

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 1 times in TR Web of Science
Scopus Citation Count Cited 1 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 50 Abstract Views, 2 File Downloads  -  Detailed Statistics
Created: Wed, 14 Apr 2021, 20:51:22 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.