EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Stacking Ensemble Deep Learning for Automated Broiler Breeder Feather Scoring

Stephen Afrifa, Sawyer Exum, Biswash Khatiwada, Kapalik Khanal, Edgar Oviedo-Rondón, Ramesh Bahadur Bist

AgriEngineering · 08.11.2026 · 8 (11) · 481

DOI: 10.3390/agriengineering8110481 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AgriEngineering, online erschienen am 08.11.2026. Verfasst von Stephen Afrifa und 5 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: North Carolina State University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Assessing feather condition in broiler breeders is essential for monitoring poultry welfare and identifying feather damage and loss associated with management, health, natural mating, and behavioral challenges. Feather condition can be associated with fertility failures, as featherless areas can suffer scratches from roosters during mating, reducing reproductive success. Manual feather scoring (FS) is labor-intensive, subjective, and difficult to scale in broiler breeder production. This study proposed a stacking ensemble framework for automated multiclass FS classification using RGB images. A total of 67,231 images were categorized into six FS classes (FS_0–FS_5) and used to train three independently trained models: MobileNetV2, EfficientNetB0, and ResNet50. Their class probability outputs were integrated using a Logistic Regression (LR) meta-learner. The proposed stacking ensemble achieved 99.83% accuracy, 99.83% macro precision, 99.86% macro recall, 99.84% macro F1-score, an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.9999, and a quadratic weighted kappa (QWK) of 0.9997. The QWK and ordinal error analysis indicated near-perfect chance-corrected agreement, with no severe cross-category misclassifications. Bird-grouped five-fold cross-validation showed stable performance within the experimental domain evaluated. Gradient-Weighted Class Activation Mapping (Grad-CAM) provided qualitative insight into model attention while also indicating some background activation. The proposed framework shows strong performance on a finer six-class FS task and demonstrates the potential of stacking ensemble learning for objective poultry welfare assessment. Broader cross-farm and cross-device validation remains necessary before practical deployment.

Förderung

  • North Carolina State University

Zitieren

APA

Afrifa, S., Exum, S., Khatiwada, B., Khanal, K., Oviedo-Rondón, E., & Bist, R. B. (2026). Stacking Ensemble Deep Learning for Automated Broiler Breeder Feather Scoring. AgriEngineering, 8(11), 481. https://doi.org/10.3390/agriengineering8110481

Vancouver

Afrifa S, Exum S, Khatiwada B, Khanal K, Oviedo-Rondón E, Bist RB. Stacking Ensemble Deep Learning for Automated Broiler Breeder Feather Scoring. AgriEngineering. 2026;8(11):481. doi:10.3390/agriengineering8110481

BibTeX
@article{Afrifa2026,
  author = {Afrifa, Stephen and Exum, Sawyer and Khatiwada, Biswash and Khanal, Kapalik and Oviedo-Rondón, Edgar and Bist, Ramesh Bahadur},
  title = {Stacking Ensemble Deep Learning for Automated Broiler Breeder Feather Scoring},
  journal = {AgriEngineering},
  year = {2026},
  volume = {8},
  number = {11},
  pages = {481},
  doi = {10.3390/agriengineering8110481}
}
Kostenlos starten →