EUVIMEDEUVIMED entdecken
Crossref

Evaluation of Eating Posture Detection Artificial Intelligence Models Trained on Different Supervised Datasets and Prototyping of Real‐Time Feed Intake Estimation Tool for Broilers

Tong Meng iD, Hiroki Matsuyama, Shinsuke Konno, Kenichi Horiguchi

Animal Science Journal · 2026-01 · 97 (1)

DOI: 10.1111/asj.70162 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Animal Science Journal, online erschienen am 11.03.2026. Verfasst von Tong Meng und 3 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Agriculture, Yamagata University, Yamagata, Japan. Hauptthemen laut MEDLINE: Chickens, Artificial Intelligence, Eating, Posture. Die Arbeit nennt 45 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study investigated the impact of supervised dataset content on the accuracy of object detection Artificial Intelligence (AI) model for detecting eating postures (EP) in broilers. The findings confirmed that (1) more individuals in EP did not necessarily improve the AI model's detection accuracy, and using still images with different numbers of such individuals could enhance the AI model's ability to detect EP. (2) Including both EP and postures similar to eating postures (SEP) was found to improve detection accuracy; additionally, adding still images that contain only SEP also enhanced detection accuracy; moreover, accuracy was higher when EP and SEP were included in the same still image than in separate images. (3) Ensuring an equal proportion of still images containing different numbers of individuals in EP and in SEP was necessary. Furthermore, a tool to estimate broiler feed intake in real time was prototyped. Using this tool, eight feed intake estimations of 0.5 h were conducted for five broilers under group management, resulting in the mean absolute error (MAE) of 4.3 g and the mean absolute percentage error (MAPE) of 13.3%, indicating good estimation accuracy.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ChickensArtificial IntelligenceEatingPostureDatasets as TopicFeeding BehaviorAnimalsTime Factors

Stichwörter der Autor:innen

artificial intelligencebroilerobject detectionreal‐time feed intake estimation toolsupervised dataset

Autor:innen und Institutionen

  • Faculty of Agriculture, Yamagata University, Yamagata, Japan.

ORCID-Profile: Tong Meng

Zitieren

APA

Meng, T., Matsuyama, H., Konno, S., & Horiguchi, K. (2026). Evaluation of Eating Posture Detection Artificial Intelligence Models Trained on Different Supervised Datasets and Prototyping of Real‐Time Feed Intake Estimation Tool for Broilers. Animal Science Journal, 97(1). https://doi.org/10.1111/asj.70162

Vancouver

Meng T, Matsuyama H, Konno S, Horiguchi K. Evaluation of Eating Posture Detection Artificial Intelligence Models Trained on Different Supervised Datasets and Prototyping of Real‐Time Feed Intake Estimation Tool for Broilers. Animal Science Journal. 2026;97(1). doi:10.1111/asj.70162

BibTeX
@article{Meng2026,
  author = {Meng, Tong and Matsuyama, Hiroki and Konno, Shinsuke and Horiguchi, Kenichi},
  title = {Evaluation of Eating Posture Detection Artificial Intelligence Models Trained on Different Supervised Datasets and Prototyping of Real‐Time Feed Intake Estimation Tool for Broilers},
  journal = {Animal Science Journal},
  year = {2026},
  volume = {97},
  number = {1},
  doi = {10.1111/asj.70162}
}
Kostenlos starten →