Predicting thermal trends in smart buildings using machine learning: a case study
Revista Multidisciplinaria Voces de América y el Caribe · 10.02.2026 · 3 (1) · 186-205
DOI: 10.69821/remuvac.v3i1.299 ↗Kurz gefasst
Fachartikel in der Zeitschrift Revista Multidisciplinaria Voces de América y el Caribe, online erschienen am 10.02.2026. Verfasst von Carlos Alberto Mejía Rodriguez und 3 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
This study addresses the need to accurately anticipate outdoor temperature variations to automate responses in smart homes. The research was conducted at the Aguachica campus of Universidad Popular del Cesar, using IoT sensors to collect real-time meteorological data. A multiclass classification problem was formulated to predict thermal trends (increase, decrease, or stable) every 30 minutes. Machine learning models including Random Forest, XGBoost, and LSTM were evaluated, with Random Forest achieving the best performance in terms of precision, recall, and F1-score. The results confirm the feasibility of integrating these models into home automation systems for effective automated responses, offering a replicable methodological approach for climate intelligence in smart housing.
Zitieren
APA
Rodriguez, C. A. M., Vergel, L. M. A., Velásquez, L. X. C., & Niz, E. L. (2026). Predicting thermal trends in smart buildings using machine learning: a case study. Revista Multidisciplinaria Voces de América y el Caribe, 3(1), 186-205. https://doi.org/10.69821/remuvac.v3i1.299
Vancouver
Rodriguez CAM, Vergel LMA, Velásquez LXC, Niz EL. Predicting thermal trends in smart buildings using machine learning: a case study. Revista Multidisciplinaria Voces de América y el Caribe. 2026;3(1):186-205. doi:10.69821/remuvac.v3i1.299
BibTeX
@article{Rodriguez2026,
author = {Rodriguez, Carlos Alberto Mejía and Vergel, Lina Marcela Arévalo and Velásquez, Leidy Ximena Cortés and Niz, Edgardo Lozano},
title = {Predicting thermal trends in smart buildings using machine learning: a case study},
journal = {Revista Multidisciplinaria Voces de América y el Caribe},
year = {2026},
volume = {3},
number = {1},
pages = {186--205},
doi = {10.69821/remuvac.v3i1.299}
}
EUVIMED