EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cross-Domain Human Activity Recognition Using Low-Resolution Infrared Sensors

Guillermo Diaz, Bo Tan iD, Iker Sobron iD, Iñaki Eizmendi iD, Iratxe Landa iD, Manuel Velez iD

Sensors · 02.10.2024 · 24 (19) · 6388

DOI: 10.3390/s24196388 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 02.10.2024. Verfasst von Guillermo Diaz und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Communications Engineering, University of the Basque Country, 48013 Bilbao, Spain. Hauptthemen laut MEDLINE: Human Activities. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Basque Government, Finnish Research Council, Spanish Government.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper investigates the feasibility of cross-domain recognition for human activities captured using low-resolution 8 × 8 infrared sensors in indoor environments. To achieve this, a novel prototype recurrent convolutional network (PRCN) was evaluated using a few-shot learning strategy, classifying up to eleven activity classes in scenarios where one or two individuals engaged in daily tasks. The model was tested on two independent datasets, with real-world measurements. Initially, three different networks were compared as feature extractors within the prototype network. Following this, a cross-domain evaluation was conducted between the real datasets. The results demonstrated the model’s effectiveness, showing that it performed well regardless of the diversity of samples in the training dataset.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Human ActivitiesHumansInfrared RaysNeural Networks, ComputerAlgorithms

Stichwörter der Autor:innen

cross-domainfew-shot learninghuman activity recognitionlong short-term memory networkslow-resolution infraredprototypes networkrecurrent convolutional network

Autor:innen und Institutionen

  • Department of Communications Engineering, University of the Basque Country, 48013 Bilbao, Spain.
  • Department of Electrical Engineering, Tampere University, 33100 Tampere, Finland.
  • Department of Computer Languages and Systems, University of the Basque Country, 48013 Bilbao, Spain.

ORCID-Profile: Bo Tan, Iker Sobron, Iñaki Eizmendi, Iratxe Landa, Manuel Velez

Förderung

  • Basque Government
  • Finnish Research Council
  • Spanish Government
  • Spanish State Research Agency
  • Finnish Research Council: SPHERE-DNA project

Zitieren

APA

Diaz, G., Tan, B., Sobron, I., Eizmendi, I., Landa, I., & Velez, M. (2024). Cross-Domain Human Activity Recognition Using Low-Resolution Infrared Sensors. Sensors, 24(19), 6388. https://doi.org/10.3390/s24196388

Vancouver

Diaz G, Tan B, Sobron I, Eizmendi I, Landa I, Velez M. Cross-Domain Human Activity Recognition Using Low-Resolution Infrared Sensors. Sensors. 2024;24(19):6388. doi:10.3390/s24196388

BibTeX
@article{Diaz2024,
  author = {Diaz, Guillermo and Tan, Bo and Sobron, Iker and Eizmendi, Iñaki and Landa, Iratxe and Velez, Manuel},
  title = {Cross-Domain Human Activity Recognition Using Low-Resolution Infrared Sensors},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {19},
  pages = {6388},
  doi = {10.3390/s24196388}
}
Kostenlos starten →