Related Experiment Video
Updated: Jun 24, 2026
10:07
Thermal Imaging to Study Stress Non-invasively in Unrestrained Birds
Published on: November 6, 2015
13.4K
A XGBoost-Based Prediction Method for Meat Sheep Transport Stress Using Wearable Photoelectric Sensors and Infrared
Ruiqin Ma1, Runqing Chen2, Buwen Liang2
1National Research Facility for Pheontypic and Genotypic Analysis of Model Animals (BEIJING), China Agricultural University, Beijing 100083, China.
Sensors (Basel, Switzerland)
|December 17, 2024
Summary
This study developed a biosignal monitoring system using wearable sensors to assess sheep transport stress. Machine learning models, particularly XGBoost, accurately predicted stress levels, improving animal welfare and meat quality.
Area of Science:
- Animal Science
- Biomedical Engineering
- Machine Learning
Background:
- Transportation stress negatively impacts live sheep health and meat quality.
- Existing methods for monitoring sheep during transport are insufficient.
- Hu sheep were selected as the model for meat sheep research.
Purpose of the Study:
- To develop a systematic method for detecting, processing, and modeling biosignals of sheep during transport.
- To accurately assess and classify transportation stress in meat sheep.
- To improve the reliability and safety of sheep transportation.
Main Methods:
- Wearable sensors (photoelectric, infrared temperature) were used for physiological and environmental monitoring.
- Core waveform extraction and spectral estimation identified key transport parameters.
- Machine learning algorithms (SVC, GBDT, XGBoost) were employed for stress classification.
Main Results:
- Support Vector Classification (SVC) and Gradient Boosting Decision Tree (GBDT) showed high effectiveness.
- The eXtreme Gradient Boosting (XGB) model achieved the highest classification accuracy.
- Optimized XGBoost achieved 100% accuracy in assessing transport stress states, with overall model accuracy reaching 94.92%.
Conclusions:
- The developed biosignal monitoring and machine learning approach effectively predicts transportation stress in sheep.
- This method enhances transport reliability and reduces risks associated with sheep transportation.
- The findings address challenges in supervising sheep transport and ensuring meat quality control.
