EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Edge intelligence for poultry welfare: Utilizing tiny machine learning neural network processors for vocalization analysis

Ramasamy Srinivasagan iD, Mohammed Shawky El Sayed iD, Mohammed Ibrahim Al-Rasheed, Ali Saeed Alzahrani

PLOS ONE · 2025

DOI: 10.1371/journal.pone.0316920 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, 2025. Verfasst von Ramasamy Srinivasagan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Computer Engineering, CCSIT, King Faisal University, Al Hufuf, Kingdom of Saudi Arabia. Hauptthemen laut MEDLINE: Vocalization, Animal, Machine Learning, Chickens, Neural Networks, Computer. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: King Faisal University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The health of poultry flock is crucial in sustainable farming. Recent advances in machine learning and speech analysis have opened up opportunities for real-time monitoring of the behavior and health of flock. However, there has been little research on using Tiny Machine Learning (Tiny ML) for continuous vocalization monitoring in poultry. This study addresses this gap by developing and deploying Tiny ML models on low-power edge devices to monitor chicken vocalizations. The focus is on overcoming challenges such as memory limitations, processing power, and battery life to ensure practical implementation in agricultural settings. In collaboration with avian researchers, a diverse dataset of poultry vocalizations representing a range of health and environmental conditions was created to train and validate the algorithms. Digital Signal Processing (DSP) blocks of the Edge Impulse platform were used to generate spectral features for studying fowl vocalization. A one-dimensional Convolutional Neural Network (CNN) model was employed for classification. The study emphasizes accurately identifying and categorizing different chicken noises associated with emotional states such as discomfort, hunger, and satisfaction. To improve accuracy and reduce background noise, noise-robust Tiny ML algorithms were developed. Before the removal of background noise, our average accuracy and F1 scores were 91.6% and 0.92, respectively. After the removal, they improved to 96.6% and 0.95.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Vocalization, AnimalMachine LearningChickensNeural Networks, ComputerAnimal WelfareAnimalsAlgorithmsSignal Processing, Computer-Assisted

Autor:innen und Institutionen

  • Computer Engineering, CCSIT, King Faisal University, Al Hufuf, Kingdom of Saudi Arabia.
  • Avian Research Center, King Faisal University, Al-Ahsa, Saudi Arabia.
  • College of Veterinary Medicine, King Faisal University, Al-Ahsa, Saudi Arabia.

ORCID-Profile: Ramasamy Srinivasagan, Mohammed Shawky El Sayed

Förderung

  • King Faisal University

Zitieren

APA

Srinivasagan, R., El Sayed, M. S., Al-Rasheed, M. I., & Alzahrani, A. S. (2025). Edge intelligence for poultry welfare: Utilizing tiny machine learning neural network processors for vocalization analysis. PLOS ONE. https://doi.org/10.1371/journal.pone.0316920

Vancouver

Srinivasagan R, El Sayed MS, Al-Rasheed MI, Alzahrani AS. Edge intelligence for poultry welfare: Utilizing tiny machine learning neural network processors for vocalization analysis. PLOS ONE. 2025. doi:10.1371/journal.pone.0316920

BibTeX
@article{Srinivasagan2025,
  author = {Srinivasagan, Ramasamy and El Sayed, Mohammed Shawky and Al-Rasheed, Mohammed Ibrahim and Alzahrani, Ali Saeed},
  title = {Edge intelligence for poultry welfare: Utilizing tiny machine learning neural network processors for vocalization analysis},
  journal = {PLOS ONE},
  year = {2025},
  doi = {10.1371/journal.pone.0316920}
}
Kostenlos starten →