Communications of the ACM
ML Can Identify Baboon Grooming Behavior from Acceleration Signals
Said Charlotte Christensen of the University of Zurich, "Our findings have important implications for the study of social behavior in animals, particularly in non-human primates."
Credit: Charlotte Christensen
Researchers at the U.K.'s Swansea University, South Africa's University of Cape Town, and Germany's Max Planck Institute of Animal Behavior used machine learning (ML) to monitor social grooming behavior in wild baboons.
Swansea researchers developed accelerometer-equipped collars that recorded baboon activity, including grooming.
The team trained a supervised ML algorithm on acceleration data matched to baboon video recordings to recognize grooming behavior with high accuracy, then applied it to acceleration data from a dozen baboons.
Swansea's Ines Fürtbauer said, "The ability to collect and analyze continuous grooming data in wild populations will allow researchers to re-examine long-standing questions and address new ones regarding the formation and maintenance of social bonds, as well as the mechanisms underpinning the sociality-health-fitness relationship."
From Swansea University (U.K.)
View Full Article
Abstracts Copyright © 2023 SmithBucklin, Washington, D.C., USA
No entries found