Files and links (2)
Quantifying Finer-scale Behaviours Using Selforganising Maps (SOMs) to Link Accelerometery Signatures With Behavioural Patterns in Freeroaming Terrestrial Animals253.08 kB
Preprint VersionCC BY V4.0, Open Access
Preprint
Quantifying Finer-scale Behaviours Using Selforganising Maps (SOMs) to Link Accelerometery Signatures With Behavioural Patterns in Freeroaming Terrestrial Animals
Research Square, Vol.16 January 2021
Research Square Company
2021
Abstract
Collecting quantitative information on animal behaviours is dicult, especially from cryptic species or species that alter natural behaviours in the presence of humans. We develop a methodology that can precisely classify ner-scale behaviours in free roaming animals. We deployed harness-mounted tri axial accelerometers on 10 free-roaming domestic cats (Felis Catus) over eight days. We also tested two treatments using a prey protector device designed to reduce prey capture. We aligned accelerometer traces collected at 50Hz with video les (60 fps) and labelled 12 individual behaviours, then trained a supervised machine-learning algorithm using Kohonen super Self-Organising Maps (SOM). The SOM was able to predict individual behaviours with a ~ 99% overall accuracy. There was a signicant effect of sample size, with precision and sensitivity decreasing rapidly below 2,000 1-second observations. We were also able to detect a behaviour specic reduction in the predictability when cats were tted with the prey-protector device indicating the it alters biomechanical gait. Our results can be applied in movement ecology, zoology and conservation, where habitat specic movement performance between predators or prey may be critical to managing species of conservation signicance, or in veterinary and agricultural elds, where early detection of movement pathologies can improve animal welfare.
Details
- Title
- Quantifying Finer-scale Behaviours Using Selforganising Maps (SOMs) to Link Accelerometery Signatures With Behavioural Patterns in Freeroaming Terrestrial Animals
- Authors
- Nicole Galea (Author) - University of the Sunshine Coast, Queensland, School of Science and Engineering - LegacyFern Murphy (Author) - University of the Sunshine Coast, Queensland, School of Science and Engineering - LegacyJoshua Gaschk (Author) - University of the Sunshine Coast, Queensland, School of Science and Engineering - LegacyDavid Schoeman (Author) - University of the Sunshine Coast, Queensland, School of Science and Engineering - LegacyChristofer Clemente (Author) - University of the Sunshine Coast, Queensland, School of Science and Engineering - Legacy
- Publication details
- Research Square, Vol.16 January 2021
- Publisher
- Research Square Company
- Date published
- 2021
- DOI
- 10.21203/rs.3.rs-144749/v1
- ISSN
- 2693-5015
- Copyright note
- This work is licensed under a CC BY 4.0 License.
- Organisation Unit
- School of Science and Engineering - Legacy; University of the Sunshine Coast, Queensland; School of Science, Technology and Engineering
- Language
- English
- Record Identifier
- 99510607102621
- Output Type
- Preprint
Metrics
8 File views/ downloads
62 Record Views