EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Fine-Grained Human Activity Recognition in Domestic Settings Using Ultra-Wideband Radar: A Comparative Study of Deep Learning Models

Muhammad Amjad Raza iD, Nasir Mehmood, Hafeez Ur Rehman Siddiqui iD, Adil Ali Saleem iD, Lázaro Javier Hernández Rodríguez, Pablo Herrero García, Isabel de la Torre Díez

Sensors · 23.10.2026 · 26 (21) · 6714

DOI: 10.3390/s26216714 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Sensors, online erschienen am 23.10.2026. 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, Pakistan. Hauptthemen laut MEDLINE: Deep Learning, Radar, Human Activities. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human activity recognition with ultra-wideband (UWB) radar offers contactless, privacy-preserving monitoring of daily living, but distinguishing fine-grained activities performed in the same posture remains difficult. We recorded nine daily activities from 30 participants with a single PulsON 410 radar (3.1–5.3 GHz); seven are performed seated in the same chair and differ only by subtle hand and arm motions. Each 15 s recording is a 120×1440 channel–impulse–response matrix, preprocessed by background subtraction, two-dimensional wavelet denoising and standardization. Six deep learning models (Transformer, CNN-LSTM, 1D-CNN, LSTM, GRU and MLP) and a soft-voting ensemble were compared with participant-independent splits (22 training, 3 validation and 5 test participants) and five-fold cross-validation. The Transformer reached the highest cross-validation accuracy (97.74±0.30%). On the held-out participants, the Transformer (97.16%), 1D-CNN (96.93%) and GRU (96.45%) performed similarly, ahead of the CNN-LSTM, LSTM and MLP (87.47%), and a three-model ensemble reached 98.35%. Two additional participant splits and a retrained re-run confirmed that the MLP is clearly the weakest model, but the order of the other models changed by several points between runs; in the re-run, an ensemble of all six models did not exceed the Transformer (97.74%), and a range–Doppler baseline reached only 50.63%. Eating versus drinking tea and mobile phone use versus reading or sitting idle were the most confused pairs. Given the small test cohort and the controlled setting, the results are indicative rather than definitive.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningRadarHuman ActivitiesHumansLong Short Term MemoryActivities of Daily LivingFemaleConvolutional Neural NetworksAdultMale

Stichwörter der Autor:innen

convolutional neural networkdeep learningensemble learningfine-grained activitieshuman activity recognitionsedentary activitiessmart healthcaretransformerultra-wideband radar

Autor:innen und Institutionen

  • Institute of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Abu Dhabi Road, Rahim Yar Khan 64200, Pakistan.
  • Departamento de Soluciones Tecnológicas y Sistemas, Escuela Politécnica Superior, Universidad Europea del Atlántico, Isabel Torres 21, 39011 Santander, Spain.
  • Departamento de Ciencias de la Computación, Universidad Internacional Iberoamericana, Campeche 24560, Mexico.
  • Department of Computer Science, Universidad Internacional Iberoamericana, Arecibo, PR 00612, USA.
  • Departamento de Ciencias de la Computación, Fundación Universitaria Internacional de Colombia, Bogotá 110911, Colombia.
  • Departamento de Ciências da Computação, Universidade Internacional do Cuanza, Cuito, Angola.

ORCID-Profile: Muhammad Amjad Raza, Hafeez Ur Rehman Siddiqui, Adil Ali Saleem

Zitieren

APA

Raza, M. A., Mehmood, N., Siddiqui, H. U. R., Saleem, A. A., Rodríguez, L. J. H., García, P. H., & Torre Díez, I. (2026). Fine-Grained Human Activity Recognition in Domestic Settings Using Ultra-Wideband Radar: A Comparative Study of Deep Learning Models. Sensors, 26(21), 6714. https://doi.org/10.3390/s26216714

Vancouver

Raza MA, Mehmood N, Siddiqui HUR, Saleem AA, Rodríguez LJH, García PH, et al. Fine-Grained Human Activity Recognition in Domestic Settings Using Ultra-Wideband Radar: A Comparative Study of Deep Learning Models. Sensors. 2026;26(21):6714. doi:10.3390/s26216714

BibTeX
@article{Raza2026,
  author = {Raza, Muhammad Amjad and Mehmood, Nasir and Siddiqui, Hafeez Ur Rehman and Saleem, Adil Ali and Rodríguez, Lázaro Javier Hernández and García, Pablo Herrero and Torre Díez, Isabel de la},
  title = {Fine-Grained Human Activity Recognition in Domestic Settings Using Ultra-Wideband Radar: A Comparative Study of Deep Learning Models},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {6714},
  doi = {10.3390/s26216714}
}
Kostenlos starten →