EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Smart Home Digital Twin to Support the Recognition of Activities of Daily Living

Damien Bouchabou iD, Juliette Grosset iD, Sao Mai Nguyen iD, Christophe Lohr iD, Xavier Puig

Sensors · 01.09.2023 · 23 (17) · 7586

DOI: 10.3390/s23177586 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 01.09.2023. Verfasst von Damien Bouchabou und 4 weiteren Autor:innen. Beteiligte Einrichtung: IMT Atlantique, 44300 Nantes, France. Hauptthemen laut MEDLINE: Activities of Daily Living. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Brest Metropole, the region of Brittany and the European Regional Development Fund (ERDF), Delta Dore, National Association of Technical Research (ANRT).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

One of the challenges in the field of human activity recognition in smart homes based on IoT sensors is the variability in the recorded data. This variability arises from differences in home configurations, sensor network setups, and the number and habits of inhabitants, resulting in a lack of data that accurately represent the application environment. Although simulators have been proposed in the literature to generate data, they fail to bridge the gap between training and field data or produce diverse datasets. In this article, we propose a solution to address this issue by leveraging the concept of digital twins to reduce the disparity between training and real-world data and generate more varied datasets. We introduce the Virtual Smart Home, a simulator specifically designed for modeling daily life activities in smart homes, which is adapted from the Virtual Home simulator. To assess its realism, we compare a set of activity data recorded in a real-life smart apartment with its replication in the VirtualSmartHome simulator. Additionally, we demonstrate that an activity recognition algorithm trained on the data generated by the VirtualSmartHome simulator can be successfully validated using real-life field data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Activities of Daily LivingHumansPattern Recognition, AutomatedAlgorithmsRecordsHabits

Stichwörter der Autor:innen

databasedigital twinhome automationmachine learningsimulatorsmart hometransfer learning

Autor:innen und Institutionen

  • IMT Atlantique, 44300 Nantes, France.
  • U2IS, ENSTA Paris, 91120 Palaiseau, France.
  • ECAM Rennes, 35170 Bruz, France.
  • FAIR, Menlo Park, CA 94025, USA.

ORCID-Profile: Damien Bouchabou, Juliette Grosset, Sao Mai Nguyen, Christophe Lohr

Förderung

  • Brest Metropole, the region of Brittany and the European Regional Development Fund (ERDF)
  • Delta Dore
  • National Association of Technical Research (ANRT)
  • AID Project ACoCaTherm

Zitieren

APA

Bouchabou, D., Grosset, J., Nguyen, S. M., Lohr, C., & Puig, X. (2023). A Smart Home Digital Twin to Support the Recognition of Activities of Daily Living. Sensors, 23(17), 7586. https://doi.org/10.3390/s23177586

Vancouver

Bouchabou D, Grosset J, Nguyen SM, Lohr C, Puig X. A Smart Home Digital Twin to Support the Recognition of Activities of Daily Living. Sensors. 2023;23(17):7586. doi:10.3390/s23177586

BibTeX
@article{Bouchabou2023,
  author = {Bouchabou, Damien and Grosset, Juliette and Nguyen, Sao Mai and Lohr, Christophe and Puig, Xavier},
  title = {A Smart Home Digital Twin to Support the Recognition of Activities of Daily Living},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {17},
  pages = {7586},
  doi = {10.3390/s23177586}
}
Kostenlos starten →