EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Human Activity Recognition in Domestic Settings Based on Optical Techniques and Ensemble Models

Muhammad Amjad Raza iD, Nasir Mehmood, Hafeez Ur Rehman Siddiqui iD, Adil Ali Saleem iD, Roberto Marcelo Alvarez iD, Yini Airet Miró Vera iD, Isabel de la Torre Díez

Sensors · 2026

DOI: 10.3390/s26051516 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Muhammad Amjad Raza und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Abu Dhabi Road, Rahim Yar Khan 64200, Punjab, Paki…. Hauptthemen laut MEDLINE: Human Activities. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human activity recognition (HAR) is essential in many applications, such as smart homes, assisted living, healthcare monitoring, rehabilitation, physiotherapy, and geriatric care. Conventional methods of HAR use wearable sensors, e.g., acceleration sensors and gyroscopes. However, they are limited by issues such as sensitivity to position, user inconvenience, and potential health risks with long-term use. Optical camera systems that are vision-based provide an alternative that is not intrusive; however, they are susceptible to variations in lighting, intrusions, and privacy issues. The paper uses an optical method of recognizing human domestic activities based on pose estimation and deep learning ensemble models. The skeletal keypoint features proposed in the current methodology are extracted from video data using PoseNet to generate a privacy-preserving representation that captures key motion dynamics without being sensitive to changes in appearance. A total of 30 subjects (15 male and 15 female) were sampled across 2734 activity samples, including nine daily domestic activities. There were six deep learning architectures, namely, the Transformer (Transformer), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Multilayer Perceptron (MLP), One-Dimensional Convolutional Neural Network (1D CNN), and a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) architecture. The results on the hold-out test set show that the CNN–LSTM architecture achieves an accuracy of 98.78% within our experimental setting. Leave-One-Subject-Out cross-validation further confirms robust generalization across unseen individuals, with CNN–LSTM achieving a mean accuracy of 97.21% ± 1.84% across 30 subjects. The results demonstrate that vision-based pose estimation with deep learning is a useful, precise, and non-intrusive approach to HAR in smart healthcare and home automation systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Human ActivitiesHumansFemaleDeep LearningLong Short Term MemoryMaleConvolutional Neural NetworksActivities of Daily LivingMultilayer PerceptronsAlgorithms

Stichwörter der Autor:innen

CNNLSTMPoseNetTransformerdeep learninghuman activity recognitionskeleton-based recognitionsmart home

Autor:innen und Institutionen

  • Institute of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Abu Dhabi Road, Rahim Yar Khan 64200, Punjab, Pakistan.
  • Higher Polytechnic School, Universidad Europea del Atlántico, Isabel Torres 21, 39011 Santander, Spain.
  • Project Management, Universidad Internacional Iberoamericana, Arecibo, PR 00613, USA.
  • Department of Project, Universidade Internacional do Cuanza, Cuito EN250, Bié, Angola.
  • Department of Project Management, Universidad Internacional Iberoamericana, Campeche 24560, Mexico.
  • Department of Project Management, La Fundación Universitaria Internacional de Colombia, Bogotá 110911, Colombia.

ORCID-Profile: Muhammad Amjad Raza, Hafeez Ur Rehman Siddiqui, Adil Ali Saleem, Roberto Marcelo Alvarez, Yini Airet Miró Vera

Zitieren

APA

Raza, M. A., Mehmood, N., Siddiqui, H. U. R., Saleem, A. A., Alvarez, R. M., Vera, Y. A. M., & Díez, I. T. (2026). Human Activity Recognition in Domestic Settings Based on Optical Techniques and Ensemble Models. Sensors. https://doi.org/10.3390/s26051516

Vancouver

Raza MA, Mehmood N, Siddiqui HUR, Saleem AA, Alvarez RM, Vera YAM, et al. Human Activity Recognition in Domestic Settings Based on Optical Techniques and Ensemble Models. Sensors. 2026. doi:10.3390/s26051516

BibTeX
@article{Raza2026,
  author = {Raza, Muhammad Amjad and Mehmood, Nasir and Siddiqui, Hafeez Ur Rehman and Saleem, Adil Ali and Alvarez, Roberto Marcelo and Vera, Yini Airet Miró and Díez, Isabel de la Torre},
  title = {Human Activity Recognition in Domestic Settings Based on Optical Techniques and Ensemble Models},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26051516}
}
Kostenlos starten →