EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Personalized Smart Home Automation Using Machine Learning: Predicting User Activities

Mark M Gad, Walaa Gad iD, Tamer Abdelkader iD, Kshirasagar Naik iD

Sensors · 02.10.2025 · 25 (19) · 6082

DOI: 10.3390/s25196082 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 02.10.2025. Verfasst von Mark M Gad und 3 weiteren Autor:innen. Beteiligte Einrichtung: Media Engineering and Technology (MET) Department, German University in Cairo, Cairo 11835, Egypt. Hauptthemen laut MEDLINE: Machine Learning, Automation. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A personalized framework for smart home automation is introduced, utilizing machine learning to predict user activities and allow for the context-aware control of living spaces. Predicting user activities, such as ‘Watch_TV’, ‘Sleep’, ‘Work_On_Computer’, and ‘Cook_Dinner’, is essential for improving occupant comfort, optimizing energy consumption, and offering proactive support in smart home settings. The Edge Light Human Activity Recognition Predictor, or EL-HARP, is the main prediction model used in this framework to predict user behavior. The system combines open-source software for real-time sensing, facial recognition, and appliance control with affordable hardware, including the Raspberry Pi 5, ESP32-CAM, Tuya smart switches, NFC (Near Field Communication), and ultrasonic sensors. In order to predict daily user activities, three gradient-boosting models—XGBoost, CatBoost, and LightGBM (Gradient Boosting Models)—are trained for each household using engineered features and past behaviour patterns. Using extended temporal features, LightGBM in particular achieves strong predictive performance within EL-HARP. The framework is optimized for edge deployment with efficient training, regularization, and class imbalance handling. A fully functional prototype demonstrates real-time performance and adaptability to individual behavior patterns. This work contributes a scalable, privacy-preserving, and user-centric approach to intelligent home automation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningAutomationHumansAlgorithmsSoftware

Stichwörter der Autor:innen

context-aware systemsedge computinggradient boosting modelshuman activity recognitionintelligent environmentsmachine learningpersonalizationsmart home automation

Autor:innen und Institutionen

  • Media Engineering and Technology (MET) Department, German University in Cairo, Cairo 11835, Egypt.
  • Faculty of Computer and Information Sciences, Ain Shams University, Cairo 11566, Egypt.
  • Faculty of Computer Science and Engineering, Galala University, Suez 435611, Egypt.
  • Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada.

ORCID-Profile: Walaa Gad, Tamer Abdelkader, Kshirasagar Naik

Zitieren

APA

Gad, M. M., Gad, W., Abdelkader, T., & Naik, K. (2025). Personalized Smart Home Automation Using Machine Learning: Predicting User Activities. Sensors, 25(19), 6082. https://doi.org/10.3390/s25196082

Vancouver

Gad MM, Gad W, Abdelkader T, Naik K. Personalized Smart Home Automation Using Machine Learning: Predicting User Activities. Sensors. 2025;25(19):6082. doi:10.3390/s25196082

BibTeX
@article{Gad2025,
  author = {Gad, Mark M and Gad, Walaa and Abdelkader, Tamer and Naik, Kshirasagar},
  title = {Personalized Smart Home Automation Using Machine Learning: Predicting User Activities},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {19},
  pages = {6082},
  doi = {10.3390/s25196082}
}
Kostenlos starten →