What question did this study set out to answer?

This study aims to evaluate different machine learning algorithms to predict body carcass fat in ewes more accurately than traditional methods.

February 25, 2026Agriculture2 citationsOpen Access

Comparative Evaluation of Machine Learning Algorithms for Predicting Body Carcass Fat in Ewes

Designing Predictive Models: A Comparative Evaluation of Machine Learning Algorithms for Predicting Body Carcass Fat in Ewes at Weaning

View Full Paper

Ask AI

Bookmark

Authors

Comparative analysis evaluates machine learning algorithms for body carcass fat prediction in ewes, suggesting advancements in assessment methods.

This study aims to evaluate different machine learning algorithms to predict body carcass fat in ewes more accurately than traditional methods.
Eight machine learning models were compared, including four non-linear regression methods and four neural networks.
A dataset of 74 Coopworth ewes with 13 independent variables was used.
The dataset was divided into training, validation, and testing sets (52, 11, and 11 ewes respectively).
Model performance was measured using R2 values based on weight and RGB-image-based measurements.
The Gradient Boosting Regression model achieved the highest predictive accuracy with an R2 value of 0.9434.
The Ensemble Neural Network followed with an R2 value of 0.9371, also utilizing body weight data.
Image analysis BCF values were validated against computerized tomography, validating the new methods' accuracy.

Shalaldeh et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

February 25, 2026Agriculture2 citationsOpen Access

Designing Predictive Models: A Comparative Evaluation of Machine Learning Algorithms for Predicting Body Carcass Fat in Ewes at Weaning

View Full Paper

Ask AI

Bookmark

Authors

Comparative analysis evaluates machine learning algorithms for body carcass fat prediction in ewes, suggesting advancements in assessment methods.

This study aims to evaluate different machine learning algorithms to predict body carcass fat in ewes more accurately than traditional methods.
Eight machine learning models were compared, including four non-linear regression methods and four neural networks.
A dataset of 74 Coopworth ewes with 13 independent variables was used.
The dataset was divided into training, validation, and testing sets (52, 11, and 11 ewes respectively).
Model performance was measured using R2 values based on weight and RGB-image-based measurements.
The Gradient Boosting Regression model achieved the highest predictive accuracy with an R2 value of 0.9434.
The Ensemble Neural Network followed with an R2 value of 0.9371, also utilizing body weight data.
Image analysis BCF values were validated against computerized tomography, validating the new methods' accuracy.

Shalaldeh et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark