Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1002/ecy.3251 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Behavioural context of call production in humpback whale calves: identification of potential begging calls in a mysticetes species.
Proc Biol Sci
December 2024
Institut des Neurosciences Paris-Saclay, Université Paris-Saclay, CNRS, Saclay, France.
Article Synopsis
- Baleen whale calves produce vocalizations that play a significant role in mother-calf interactions, although the specific behavioral context of these calls is not fully understood.
- Researchers used multi-sensor tags to study the relationships between call types and behavioral states in humpback whale calves, finding that certain behaviors like suckling and play are associated with higher rates of calling.
- The study identifies different call types related to specific activities, highlighting the importance of vocal signaling for communication and development between mother-calf pairs in baleen whales.
Identifying prey capture events of a free-ranging marine predator using bio-logger data and deep learning.
R Soc Open Sci
June 2024
Department of Statistical Sciences, Centre for Statistics in Ecology, Environment and Conservation (SEEC), University of Cape Town, Cape Town 7701, South Africa.
Marine predators are integral to the functioning of marine ecosystems, and their consumption requirements should be integrated into ecosystem-based management policies. However, estimating prey consumption in diving marine predators requires innovative methods as predator-prey interactions are rarely observable. We developed a novel method, validated by animal-borne video, that uses tri-axial acceleration and depth data to quantify prey capture rates in chinstrap penguins ().
View Article and Find Full Text PDFA method to estimate prey density from single-camera images: A case study with chinstrap penguins and Antarctic krill.
PLoS One
July 2024
Antarctic Ecosystem Research Division, Southwest Fisheries Science Center, National Marine Fisheries Service, National Oceanic and Atmospheric Administration, La Jolla, CA, United States of America.
Article Synopsis
- Researchers developed a new method to estimate the density of Antarctic krill from video footage taken by a chinstrap penguin in Antarctica, utilizing a machine learning model to identify krill in the frames.
- The model achieved a 73% overall accuracy and identified krill frames with an 83% positive predictive value, helping to analyze the foraging behavior of the penguin.
- The estimated krill density varied between 2 to 307 krill per cubic meter, providing insights into prey availability that could impact predator foraging efficiency, and this technique could be applied to other marine predators as well.
Machine Learning Methods and Visual Observations to Categorize Behavior of Grazing Cattle Using Accelerometer Signals.
Sensors (Basel)
May 2024
Quantitative Ecology and Spatial Technologies Laboratory, Department of Wildlife, Fisheries and Aquaculture, Mississippi State University, Starkville, MS 39762, USA.
Accelerometers worn by animals produce distinct behavioral signatures, which can be classified accurately using machine learning methods such as random forest decision trees. The objective of this study was to identify accelerometer signal separation among parsimonious behaviors. We achieved this objective by (1) describing functional differences in accelerometer signals among discrete behaviors, (2) identifying the optimal window size for signal pre-processing, and (3) demonstrating the number of observations required to achieve the desired level of model accuracy,.
View Article and Find Full Text PDFObserving animals in the wild often poses extreme challenges, but animal-borne accelerometers are increasingly revealing unobservable behaviours. Automated machine learning streamlines behaviour identification from the substantial datasets generated during multi-animal, long-term studies; however, the accuracy of such models depends on the qualities of the training data. We examined how data processing influenced the predictive accuracy of random forest (RF) models, leveraging the easily observed domestic cat () as a model organism for terrestrial mammalian behaviours.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!