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

Evaluating community pharmacists' practices in managing insomnia in Saudi Arabia: a cross-sectional study using simulated patient visits.

Frontiers in public health·2026
Same author

Light Attention Encoder-Decoder for Cattle Body Segmentation and Body Weight Estimation.

Animals : an open access journal from MDPI·2026
Same author

Disruption of BnPHT5;1b gene enhances arsenate tolerance through increased arsenate retention in shoot cell walls of Brassica napus.

Journal of hazardous materials·2026
Same author

Starches from Different Tiger Nut Varieties: A Comparative Study of Multi-Scale Structural Characteristics, Functional Properties, and In Vitro Digestibility.

Foods (Basel, Switzerland)·2026
Same author

Impact of Trait Measurement Error on Quantitative Genetic Analysis of Computer Vision-Derived Traits.

Genes·2026
Same author

Artificial intelligence in animal breeding and genetics: applications, opportunities, and challenges.

Animal frontiers : the review magazine of animal agriculture·2026

Related Experiment Video

Updated: Aug 30, 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

Improved pig behavior analysis by optimizing window sizes for individual behaviors on acceleration and angular

Saleh Alghamdi1, Zhuqing Zhao1, Dong S Ha1

  • 1The Bradley Department of Electrical Engineering, Virginia Polytechnic Institute and State University, Blacksburg, VA 24061, USA.

Journal of Animal Science
|September 3, 2022
PubMed
Summary

Machine learning accurately identifies pig behaviors using wireless sensors. Optimized window and step sizes enhance classification performance for activities like eating and walking.

Keywords:
data segmentationlabelingpig behavior classificationpig behavior monitoringwindow sizewireless sensor node

More Related Videos

A Novel Single Animal Motor Function Tracking System Using Simple, Readily Available Software
08:22

A Novel Single Animal Motor Function Tracking System Using Simple, Readily Available Software

Published on: August 31, 2018

6.6K
Automated, Quantitative Cognitive/Behavioral Screening of Mice: For Genetics, Pharmacology, Animal Cognition and Undergraduate Instruction
16:23

Automated, Quantitative Cognitive/Behavioral Screening of Mice: For Genetics, Pharmacology, Animal Cognition and Undergraduate Instruction

Published on: February 26, 2014

14.4K

Related Experiment Videos

Last Updated: Aug 30, 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 Novel Single Animal Motor Function Tracking System Using Simple, Readily Available Software
08:22

A Novel Single Animal Motor Function Tracking System Using Simple, Readily Available Software

Published on: August 31, 2018

6.6K
Automated, Quantitative Cognitive/Behavioral Screening of Mice: For Genetics, Pharmacology, Animal Cognition and Undergraduate Instruction
16:23

Automated, Quantitative Cognitive/Behavioral Screening of Mice: For Genetics, Pharmacology, Animal Cognition and Undergraduate Instruction

Published on: February 26, 2014

14.4K

Area of Science:

  • Agricultural technology
  • Animal behavior monitoring
  • Machine learning applications

Background:

  • Accurate monitoring of livestock behavior is crucial for animal welfare and farm management.
  • Wireless sensor nodes offer a non-invasive method for collecting detailed physiological and motion data from animals.
  • Previous studies have explored sensor-based behavior identification, but optimizing data processing parameters remains key.

Purpose of the Study:

  • To apply machine learning algorithms for identifying specific pig behaviors using data from wireless sensor nodes.
  • To investigate the impact of varying window sizes (WS) and step sizes (SS) on behavior classification accuracy.
  • To determine the optimal WS and SS for different pig behaviors to improve identification performance.

Main Methods:

  • Collected acceleration and angular velocity data from pigs using wireless sensor nodes over 131 hours.
  • Utilized video cameras for ground truth annotation of pig behaviors.
  • Segmented sensor data using adaptive window and step sizes, testing multiple combinations.
  • Compared the performance of five machine learning algorithms: support vector machine, k-nearest neighbors, decision trees, naive Bayes, and random forest (RF).

Main Results:

  • The random forest (RF) algorithm achieved the highest overall F1 score of 92.36% for four major behaviors.
  • Specific F1 scores for RF were: 0.98 for "eating," 0.99 for "lying," 0.93 for "walking," and 0.91 for "standing."
  • Optimal window sizes were determined as 7 seconds for "eating" and "lying," and 3 seconds for "walking" and "standing."

Conclusions:

  • Machine learning, particularly RF, effectively identifies pig behaviors from wireless sensor data.
  • Adaptive window and step sizes significantly improve classification performance based on behavior duration.
  • This approach offers a promising tool for precision livestock farming and enhanced animal welfare monitoring.