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

Urine, saliva, and serum metabolomics predict female pig reproductive potential status using machine learning modelling.

Reproduction (Cambridge, England)·2026
Same author

Prediction of Pellet Durability Index in a commercial feed mill using multiple linear regression with variable selection and dimensionality reduction.

Journal of animal science·2025
Same author

Machine-Learning-Based Genome-Wide Association Studies for Uncovering QTL Underlying Soybean Yield and Its Components.

International journal of molecular sciences·2022
Same author

Application of machine learning and genetic optimization algorithms for modeling and optimizing soybean yield using its component traits.

PloS one·2021
Same author

A review of traditional and machine learning methods applied to animal breeding.

Animal health research reviews·2020
Same author

Pairwise visual comparison of small RNA secondary structures with base pair probabilities.

BMC bioinformatics·2019

Related Experiment Video

Updated: Jul 14, 2025

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs
06:30

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs

Published on: June 5, 2019

8.5K

A computer vision image differential approach for automatic detection of aggressive behavior in pigs using deep

Jasmine Fraser1, Harry Aricibasi2, Dan Tulpan1

  • 1Department of Animal Biosciences, Ontario Agricultural College, University of Guelph, 50 Stone Road East, Guelph, ON, CanadaN1G2W1.

Journal of Animal Science
|October 9, 2023
PubMed
Summary

Deep learning accurately detects pig aggression using convolutional neural networks (CNNs) and image differentials. This efficient system aids animal welfare and productivity by identifying aggressive behaviors in real-time.

Keywords:
aggressive behaviorcomputer visiondeep learningimage analysispig behaviorvideo recording

More Related Videos

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.4K
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

448

Related Experiment Videos

Last Updated: Jul 14, 2025

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs
06:30

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs

Published on: June 5, 2019

8.5K
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.4K
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

448

Area of Science:

  • Animal Behavior
  • Machine Learning
  • Computer Vision

Background:

  • Pig aggression negatively impacts animal welfare and farm productivity.
  • Automated detection of aggressive behaviors is crucial for improving group-housed pig management.

Purpose of the Study:

  • To develop and evaluate a supervised deep learning (DL) approach for automatic detection of aggressive behaviors in pairs of pigs.
  • To assess the effectiveness of convolutional neural network (CNN) architectures combined with image differential techniques.

Main Methods:

  • Video recordings of unfamiliar piglet pairs were analyzed using CNN models based on VGG-16 architecture.
  • Four datasets were created using different image differencing methods (Diff1, Diff5, Diff10, blended).
  • Model performance was evaluated using accuracy, precision, recall, and area under the curve, with a 0.5 sigmoid threshold.

Main Results:

  • The stacked CNN model achieved the highest testing accuracy (0.79), precision (0.81), recall (0.77), and AUC (0.86).
  • The blended dataset approach significantly reduced training, validation, and preprocessing times, enabling real-time detection.
  • Specific behaviors like head biting and parallel pressing were classified with high recall (0.95 and 0.91).

Conclusions:

  • A CNN and image differential-based DL approach is effective and computationally efficient for detecting pig aggression.
  • The developed system meets real-time requirements for practical application in swine management.
  • This technology can contribute to enhanced animal welfare and improved farm productivity.