Abstract
The development of multisensor animal-attached tags, recording data at high frequencies, has enormous potential in allowing us to define animal behaviour. The high volumes of data, are pushing us towards machine-learning as a powerful option for distilling out behaviours. However, with increasing parallel lines of data, systems become more likely to become processor limited and thereby take appreciable amounts of time to resolve behaviours. We suggest a Boolean approach whereby critical changes in recorded parameters are used as sequential templates with defined flexibility (in both time and degree) to determine individual behavioural elements within a behavioural sequence that, together, makes up a single, defined behaviour. We tested this approach, and compared it to a suite of other behavioural identification methods, on a number of behaviours from tag-equipped animals; sheep grazing, penguins walking, cheetah stalking prey and condors thermalling. Overall behaviour recognition using our new approach was better than most other methods due to; (1) its ability to deal with behavioural variation and (2) the speed with which the task was completed because extraneous data are avoided in the process. We suggest that this approach is a promising way forward in an increasingly data-rich environment and that workers sharing algorithms can provide a powerful library for the benefit of all involved in such work.
Original language | English (US) |
---|---|
Pages (from-to) | 2206-2215 |
Number of pages | 10 |
Journal | Methods in Ecology and Evolution |
Volume | 9 |
Issue number | 11 |
DOIs | |
State | Published - Nov 2018 |
Bibliographical note
Funding Information:This research contributes to the CAASE project funded by King Abdullah University of Science and Technology (KAUST) under the KAUST Sensor Initiative. We thank SANParks and the Department of Wildlife and National Parks, Botswana for allowing our research in the Kgalagadi Transfrontier Park (Permit Number 2006-05-01 MGLM) and Mr H. McKay and Mr W. Wright for their co-operation. We also thank the Nature Conservancy for allowing the sheep work in Patagonia. The study was made possible by various grants; a Leverhulme early career fellowship (ELCS), Fundación BBVa, PICT_BID-2014-0725 (SAL), the National Geographic Global Exploration Fund (#GEFNE89-13) the Royal Society (2009/R3 JP090604), NERC (NE/I002030/1) (SMS), and the Royal Society/Wolfson Lab refurbishment scheme (R. P. W). We also thank the Lewis Foundation, South Africa, The Howard G. Buffet Foundation, National Geographic, Kanabo Conservation Link, Comanis Foundation, Panthera and the Kruger Park Marathon Club for financial support. Hannah Williams thanks the Swansea University College of Science for their continued support and we thank Krüger Werke GmbH for technical help with waterproofing.
Funding Information:
This research contributes to the CAASE project funded by King Abdullah University of Science and Technology (KAUST) under the KAUST Sensor Initiative. We thank SANParks and the Department of Wildlife and National Parks, Botswana for allowing our research in the Kgalagadi Transfrontier Park (Permit Number 2006-05-01 MGLM) and Mr H. McKay and Mr W. Wright for their co-operation. We also thank the Nature Conservancy for allowing the sheep work in Patagonia. The study was made possible by various grants; a Leverhulme early career fellowship (ELCS), FundaciD?n BBVa, PICT_BI2D0-14-0725 (SAL), the National Geographic Global Exploration Fund (#GEFNE89-13) the Royal Society (2009/R3 JP090604), NERC (NE/I002030/1) (SMS), and the Royal Society/Wolfson Lab refurbishment scheme (R. P. W). We also thank the Lewis Foundation, South Africa, The Howard G. Buffet Foundation, National Geographic, Kanabo Conservation Link, Comanis Foundation, Panthera and the Kruger Park Marathon Club for financial support. Hannah Williams thanks the Swansea University College of Science for their continued support and we thank KrD?ger Werke GmbH for technical help with waterproofing.
Publisher Copyright:
© 2018 The Authors. Methods in Ecology and Evolution © 2018 British Ecological Society
Keywords
- accelerometer
- behaviour
- behaviour identification
- bioinformatics
- software
ASJC Scopus subject areas
- Ecology, Evolution, Behavior and Systematics
- Ecological Modeling
Fingerprint
Dive into the research topics of 'Give the machine a hand: A Boolean time-based decision-tree template for rapidly finding animal behaviours in multisensor data'. Together they form a unique fingerprint.Datasets
-
Data from: Give the machine a hand: a Boolean time-based decision-tree template for rapidly finding animal behaviours in multi-sensor data
Wilson, R. P. (Creator), Holton, M. D. (Creator), di Virgilio, A. (Creator), Williams, H. (Creator), Shepard, E. L. C. (Creator), Lambertucci, S. (Creator), Quintana, F. (Creator), Sala, J. E. (Creator), Balaji, B. (Creator), Lee, E. S. (Creator), Srivastava, M. (Creator), Scantlebury, D. M. (Creator), Duarte, C. (Creator), Wilson, R. P. (Creator), Holton, M. D. (Creator), di Virgilio, A. (Creator), Williams, H. (Creator), Shepard, E. L. C. (Creator), Lambertucci, S. (Creator), Quintana, F. (Creator), Sala, J. E. (Creator), Balaji, B. (Creator), Lee, E. S. (Creator), Srivastava, M. (Creator) & Scantlebury, D. M. (Creator), Dryad Digital Repository, 2018
DOI: 10.5061/dryad.56mh682, http://hdl.handle.net/10754/664193
Dataset