Work Description

Title: Use of Computer Vision to Automate Rodent Behavioral Analysis and Refine Animal Care, using the Lesser Egyptian Jerboa (Jaculus jaculus) as a Model Embargo Deposited

h
Embargo release date
  • 01/30/2026
Attribute Value
Methodology
  • These data contains the ethograms of captive adult lesser Egyptian Jerboa. A subset of the manually encoded activity budget data was utilized to train a computer vision classifier for inferences utilized in step 4.

  • Briefly, this study can be broken into multiple parts: 1: Activity budgets of singly housed adult jerboa with standard husbandry, manually annotated by a single rater 2: Alopecia was scored per animal with standard husbandry 3: The performance* of multiple observers (n = 11) at scoring jerboa behavior was quantified using subsets of the activity budget data (*accuracy and intraclass correlation). Activity budget data was then used to train multiple classifiers to compare performance on the same subset. 4: Novel enrichment items were introduced to animals, and a computer vision classifier with additional training (as determined sufficient by the performance* of human observers) was utilized to make inferences on novel data.
Description
  • This dataset contains the results of both computer vision and human annotation of jerboa behavior. Descriptions of data acquisition and production can be found in the methods section of this record and the accompanying paper. This dataset is associated with the following publication, submitted to LabAnimal: Use of Computer Vision to Automate Rodent Behavioral Analysis and Refine Animal Care, using the Lesser Egyptian Jerboa (Jaculus jaculus) as a Model by Matthew Boulanger, Juri Miyamae, Tara Martin, Gerry Hish, and Talia Moore (see below for full citation).
Creator
Depositor
Contact information
Discipline
Resource type
Last modified
  • 06/10/2025
Published
  • 06/10/2025
Language
DOI
  • https://doi.org/10.7302/3mqd-8743
License

Remediation of Harmful Language

The University of Michigan Library aims to describe its collections in a way that respects the people and communities who create, use, and are represented in them. We encourage you to contact us anonymously if you encounter harmful or problematic language in catalog records or finding aids. More information about our policies and practices is available at Remediation of Harmful Language.