Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Rethinking resilience in dairy cattle: Farmer perceptions of a multisystemic concept.

Preventive veterinary medicine·2026
Same author

Between-country differences in the psychosocial profiles of British cattle farmers.

The Veterinary record·2025
Same author

Diurnality is consistently different between individuals and decreases with disease or stressful events in dairy calves.

Scientific reports·2025
Same author

Social dominance in calves: Automatic detection of displacements at the feeder and its associations with age, health, and feeding behaviors.

Journal of dairy science·2025
Same author

Descriptive analysis of national bovine viral diarrhoea test data in England (2016-2023).

The Veterinary record·2025
Same author

Dairy calves provided with environmental enrichment are more active, playful and have fewer feeding interruptions.

Scientific reports·2025

Related Experiment Video

Updated: Nov 23, 2025

The Use of an Automated System GreenFeed to Monitor Enteric Methane and Carbon Dioxide Emissions from Ruminant Animals
11:02

The Use of an Automated System GreenFeed to Monitor Enteric Methane and Carbon Dioxide Emissions from Ruminant Animals

Published on: September 7, 2015

22.6K

Machine Learning Algorithms to Classify and Quantify Multiple Behaviours in Dairy Calves Using a Sensor: Moving

Charles Carslake1, Jorge A Vázquez-Diosdado1, Jasmeet Kaler1

  • 1School of Veterinary Medicine and Science, Sutton Bonington Campus, University of Nottingham, Leicestershire LE12 5RD, UK.

Sensors (Basel, Switzerland)
|December 30, 2020
PubMed
Summary

Monitoring multiple calf behaviors using sensors and machine learning can improve disease prediction. This study developed an accurate system for identifying and quantifying behaviors, enhancing calf health and welfare insights.

Keywords:
behaviourcalvesmachine learningprecision livestock farmingsensor

More Related Videos

The Use of Traditional Fear Tests to Evaluate Different Emotional Circuits in Cattle
12:08

The Use of Traditional Fear Tests to Evaluate Different Emotional Circuits in Cattle

Published on: April 22, 2020

8.9K
A Pipeline using Bilateral In Utero Electroporation to Interrogate Genetic Influences on Rodent Behavior
06:59

A Pipeline using Bilateral In Utero Electroporation to Interrogate Genetic Influences on Rodent Behavior

Published on: May 21, 2020

4.4K

Related Experiment Videos

Last Updated: Nov 23, 2025

The Use of an Automated System GreenFeed to Monitor Enteric Methane and Carbon Dioxide Emissions from Ruminant Animals
11:02

The Use of an Automated System GreenFeed to Monitor Enteric Methane and Carbon Dioxide Emissions from Ruminant Animals

Published on: September 7, 2015

22.6K
The Use of Traditional Fear Tests to Evaluate Different Emotional Circuits in Cattle
12:08

The Use of Traditional Fear Tests to Evaluate Different Emotional Circuits in Cattle

Published on: April 22, 2020

8.9K
A Pipeline using Bilateral In Utero Electroporation to Interrogate Genetic Influences on Rodent Behavior
06:59

A Pipeline using Bilateral In Utero Electroporation to Interrogate Genetic Influences on Rodent Behavior

Published on: May 21, 2020

4.4K

Area of Science:

  • Animal Science
  • Machine Learning Applications
  • Veterinary Medicine

Background:

  • Sensors detecting lying and feeding behaviors offer early disease detection in calves.
  • Relying on single behavior monitoring may be insufficient for accurate disease prediction.
  • Multiple behaviors like play, grooming, and feeding are crucial for assessing calf health.

Purpose of the Study:

  • To develop and validate a machine learning approach for multi-class behavior identification in calves.
  • To create a behavior quantification algorithm to accurately estimate the prevalence of specific behaviors.
  • To assess the utility of wearable sensors for monitoring calf health and welfare.

Main Methods:

  • Thirteen pre-weaned dairy calves were equipped with collar-mounted sensors and video monitoring.
  • Behavioral observations were merged with sensor data; features were extracted using 1-10s windows.
  • An AdaBoost ensemble learning algorithm classified behaviors, followed by an adjusted count quantification algorithm.

Main Results:

  • High accuracies were achieved for identifying various behaviors: locomotor play (99.73%), self-grooming (98.18%), ruminating (94.47%), suckling (94.96-96.44%), and lying states (90.38%).
  • The quantification algorithm showed a high correlation (0.97) with the true prevalence of locomotor play.
  • The quantification method resulted in an 18.97% overestimation of locomotor play behavior prevalence.

Conclusions:

  • This study pioneers machine learning for multi-class behavior identification and quantification in calves using wearable sensors.
  • The findings provide recommendations for sampling frequencies, feature selection, and window sizes for sensor-based monitoring.
  • This approach offers significant potential for advancing the evaluation of calf health and welfare.