EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Design and Evaluation of a Smart Poultry Farm Device Integrating Internet of Things and Machine Learning for Monitoring Temperature and Humidity

Folashade Olamide Ariba, David Abolarin, John Onyemenam, Ester Toyin Olawole

Malaysian Journal of Science and Advanced Technology · 15.06.2026 · 160-168

DOI: 10.56532/k8bv4a45 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Malaysian Journal of Science and Advanced Technology, online erschienen am 15.06.2026. Verfasst von Folashade Olamide Ariba und 3 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rising global temperatures and humidity are significantly impacting birds' welfare, productivity, and mortality rates, leading to economic losses and inefficiencies in poultry farm management. This research aims to design and implement an Internet of Things (IoT) device integrated with Machine Learning (ML) models to forecast temperature and humidity values in a poultry farm. This study designed a prototype of an IoT device consisting of DHT11 sensors connected to an ESP32 microcontroller to collect real-time temperature and humidity data from a poultry farm. The collected data are used to train ML models, namely: Auto-Regressive Integrated Moving Average (ARIMA), Random Forest (RF) and Support Vector Machine (SVM) to forecast future temperature and humidity values. The measured and predicted data are displayed on an LCD screen connected to the ESP32 microcontroller, enhancing proactive decision-making. Simulation testing was carried out on Python software to compare and analyse the measured and predicted temperature and humidity values. The performance of the ML models was evaluated in terms of Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Coefficient of Determination (R2). The results show that RF predicted data gave a close fit to the actual data, SVM provided a tendency toward lower predicted value and ARIMA model showed the most accurate predictions, providing lowest RMSE (1.56) and MAE (0.34) at highest R2 (88%) than RF and SVM. This approach demonstrates that ARIMA model offers effective solution than other ML models in poultry farming through real-time monitoring and predictive analysis.

Zitieren

APA

Ariba, F. O., Abolarin, D., Onyemenam, J., & Olawole, E. T. (2026). Design and Evaluation of a Smart Poultry Farm Device Integrating Internet of Things and Machine Learning for Monitoring Temperature and Humidity. Malaysian Journal of Science and Advanced Technology, 160-168. https://doi.org/10.56532/k8bv4a45

Vancouver

Ariba FO, Abolarin D, Onyemenam J, Olawole ET. Design and Evaluation of a Smart Poultry Farm Device Integrating Internet of Things and Machine Learning for Monitoring Temperature and Humidity. Malaysian Journal of Science and Advanced Technology. 2026:160-168. doi:10.56532/k8bv4a45

BibTeX
@article{Ariba2026,
  author = {Ariba, Folashade Olamide and Abolarin, David and Onyemenam, John and Olawole, Ester Toyin},
  title = {Design and Evaluation of a Smart Poultry Farm Device Integrating Internet of Things and Machine Learning for Monitoring Temperature and Humidity},
  journal = {Malaysian Journal of Science and Advanced Technology},
  year = {2026},
  pages = {160--168},
  doi = {10.56532/k8bv4a45}
}
Kostenlos starten →