Automated Broiler Mobility Evaluation Through DL and ML Models: An Alternative Approach to Manual Gait Assessment

Broiler gait score (GS) evaluation relies on manual assessments by experts, which can be laborious, hindering timely welfare management. Deep learning (DL) models, conversely, may serve as a cost-effective solution in evaluating GS via automated detection of broiler mobility. This study aimed to dev...

Full description

Saved in:
Bibliographic Details
Main Authors: Mustafa Jaihuni, Yang Zhao, Hao Gan, Tom Tabler, Hairong Qi
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:AgriEngineering
Subjects:
Online Access:https://www.mdpi.com/2624-7402/7/5/133
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850255095146479616
author Mustafa Jaihuni
Yang Zhao
Hao Gan
Tom Tabler
Hairong Qi
author_facet Mustafa Jaihuni
Yang Zhao
Hao Gan
Tom Tabler
Hairong Qi
author_sort Mustafa Jaihuni
collection DOAJ
description Broiler gait score (GS) evaluation relies on manual assessments by experts, which can be laborious, hindering timely welfare management. Deep learning (DL) models, conversely, may serve as a cost-effective solution in evaluating GS via automated detection of broiler mobility. This study aimed to develop a vision-based YOLOv8 model to detect the locations of individual broilers, allowing for continuous tracking of birds within a pen and determining bird walking distances, speeds, idleness and movement ratios, and time at the feeder and drinker ratios. Then, Machine Learning (ML) models were developed to estimate the GS level from the mobility indicators in a lab setting. Ten broilers were color-coded and recorded via a top-view camera for 41 days. Their GS were assessed manually twice per week. The YOLOv8 model was trained, validated, and tested with 600, 150, and 50 images, respectively, and subsequently applied to the dataset yielding each broiler’s mobility indicators. The GS levels and mobility indicators were correlated through Ordinal Logistics (OL), Random Forest (RF), and Support Vector Machine (SVM) ML models. The YOLOv8 model was developed with 91% training, 89% testing, and 87% validation mean average precision (mAP) accuracies in identifying color-coded broilers. After tracking, the model estimated an average of 472.26 ± 234.18 cm hourly distance traveled and 0.13 ± 0.07 cm/s speed by a broiler. It was found that with deteriorated GS levels (i.e., worse walking ability), broilers walked shorter distances (<i>p</i> = 0.001), had lower speeds (<i>p</i> = 0.001), were increasingly idle and less mobile, and were increasingly stationed near or around the feeder. The movement ratio, average hourly walking distance, hourly average speed, and age variables were found to be the most significant variables (<i>p</i> < 0.005) in predicting GS levels. These variables were further reduced to one, the average hourly walking distance, because of high collinearity and were used to predict the GS with ML models. The RF model, outperforming others, was able to predict GS with a generalized R<sup>2</sup> of 0.62, root mean squared error (RMSE) of 0.54, and 65% classification accuracy.
format Article
id doaj-art-2467bfe713cd4868a4aae2376f40c460
institution OA Journals
issn 2624-7402
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series AgriEngineering
spelling doaj-art-2467bfe713cd4868a4aae2376f40c4602025-08-20T01:56:57ZengMDPI AGAgriEngineering2624-74022025-05-017513310.3390/agriengineering7050133Automated Broiler Mobility Evaluation Through DL and ML Models: An Alternative Approach to Manual Gait AssessmentMustafa Jaihuni0Yang Zhao1Hao Gan2Tom Tabler3Hairong Qi4Department of Animal Science, University of Tennessee, Knoxville, TN 37996, USADepartment of Animal Science, University of Tennessee, Knoxville, TN 37996, USADepartment of Biosystems Engineering and Soil Science, University of Tennessee, Knoxville, TN 37996, USADepartment of Animal Science, University of Tennessee, Knoxville, TN 37996, USADepartment of Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN 37996, USABroiler gait score (GS) evaluation relies on manual assessments by experts, which can be laborious, hindering timely welfare management. Deep learning (DL) models, conversely, may serve as a cost-effective solution in evaluating GS via automated detection of broiler mobility. This study aimed to develop a vision-based YOLOv8 model to detect the locations of individual broilers, allowing for continuous tracking of birds within a pen and determining bird walking distances, speeds, idleness and movement ratios, and time at the feeder and drinker ratios. Then, Machine Learning (ML) models were developed to estimate the GS level from the mobility indicators in a lab setting. Ten broilers were color-coded and recorded via a top-view camera for 41 days. Their GS were assessed manually twice per week. The YOLOv8 model was trained, validated, and tested with 600, 150, and 50 images, respectively, and subsequently applied to the dataset yielding each broiler’s mobility indicators. The GS levels and mobility indicators were correlated through Ordinal Logistics (OL), Random Forest (RF), and Support Vector Machine (SVM) ML models. The YOLOv8 model was developed with 91% training, 89% testing, and 87% validation mean average precision (mAP) accuracies in identifying color-coded broilers. After tracking, the model estimated an average of 472.26 ± 234.18 cm hourly distance traveled and 0.13 ± 0.07 cm/s speed by a broiler. It was found that with deteriorated GS levels (i.e., worse walking ability), broilers walked shorter distances (<i>p</i> = 0.001), had lower speeds (<i>p</i> = 0.001), were increasingly idle and less mobile, and were increasingly stationed near or around the feeder. The movement ratio, average hourly walking distance, hourly average speed, and age variables were found to be the most significant variables (<i>p</i> < 0.005) in predicting GS levels. These variables were further reduced to one, the average hourly walking distance, because of high collinearity and were used to predict the GS with ML models. The RF model, outperforming others, was able to predict GS with a generalized R<sup>2</sup> of 0.62, root mean squared error (RMSE) of 0.54, and 65% classification accuracy.https://www.mdpi.com/2624-7402/7/5/133gait scoreYOLOv8ML modelsbroiler welfare
spellingShingle Mustafa Jaihuni
Yang Zhao
Hao Gan
Tom Tabler
Hairong Qi
Automated Broiler Mobility Evaluation Through DL and ML Models: An Alternative Approach to Manual Gait Assessment
AgriEngineering
gait score
YOLOv8
ML models
broiler welfare
title Automated Broiler Mobility Evaluation Through DL and ML Models: An Alternative Approach to Manual Gait Assessment
title_full Automated Broiler Mobility Evaluation Through DL and ML Models: An Alternative Approach to Manual Gait Assessment
title_fullStr Automated Broiler Mobility Evaluation Through DL and ML Models: An Alternative Approach to Manual Gait Assessment
title_full_unstemmed Automated Broiler Mobility Evaluation Through DL and ML Models: An Alternative Approach to Manual Gait Assessment
title_short Automated Broiler Mobility Evaluation Through DL and ML Models: An Alternative Approach to Manual Gait Assessment
title_sort automated broiler mobility evaluation through dl and ml models an alternative approach to manual gait assessment
topic gait score
YOLOv8
ML models
broiler welfare
url https://www.mdpi.com/2624-7402/7/5/133
work_keys_str_mv AT mustafajaihuni automatedbroilermobilityevaluationthroughdlandmlmodelsanalternativeapproachtomanualgaitassessment
AT yangzhao automatedbroilermobilityevaluationthroughdlandmlmodelsanalternativeapproachtomanualgaitassessment
AT haogan automatedbroilermobilityevaluationthroughdlandmlmodelsanalternativeapproachtomanualgaitassessment
AT tomtabler automatedbroilermobilityevaluationthroughdlandmlmodelsanalternativeapproachtomanualgaitassessment
AT hairongqi automatedbroilermobilityevaluationthroughdlandmlmodelsanalternativeapproachtomanualgaitassessment