EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

From Lab to Real World: Assessing the Effectiveness of Human Activity Recognition and Optimization through Personalization

Marija Stojchevska iD, Mathias De Brouwer, Martijn Courteaux iD, Femke Ongenae iD, Sofie Van Hoecke iD

Sensors · 2023

DOI: 10.3390/s23104606 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Marija Stojchevska und 4 weiteren Autor:innen. Beteiligte Einrichtung: IDLab, Ghent University-imec, Technologiepark-Zwijnaarde 82, 9052 Gent, Belgium. Hauptthemen laut MEDLINE: Algorithms, Human Activities. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human activity recognition (HAR) algorithms today are designed and evaluated on data collected in controlled settings, providing limited insights into their performance in real-world situations with noisy and missing sensor data and natural human activities. We present a real-world HAR open dataset compiled from a wristband equipped with a triaxial accelerometer. During data collection, participants had autonomy in their daily life activities, and the process remained unobserved and uncontrolled. A general convolutional neural network model was trained on this dataset, achieving a mean balanced accuracy (MBA) of 80%. Personalizing the general model through transfer learning can yield comparable and even superior results using fewer data, with the MBA improving to 85%. To emphasize the issue of insufficient real-world training data, we conducted training of the model using the public MHEALTH dataset, resulting in 100% MBA. However, upon evaluating the MHEALTH-trained model on our real-world dataset, the MBA drops to 62%. After personalizing the model with real-world data, an improvement of 17% in the MBA is achieved. This paper showcases the potential of transfer learning to make HAR models trained in different contexts (lab vs. real-world) and on different participants perform well for new individuals with limited real-world labeled data available.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsHuman ActivitiesHumansData CollectionLearningNeural Networks, Computer

Stichwörter der Autor:innen

HARconvolutional neural networkshuman activity recognitionpersonalizationreal-world datatransfer learning

Autor:innen und Institutionen

  • IDLab, Ghent University-imec, Technologiepark-Zwijnaarde 82, 9052 Gent, Belgium.

ORCID-Profile: Marija Stojchevska, Martijn Courteaux, Femke Ongenae, Sofie Van Hoecke

Zitieren

APA

Stojchevska, M., De Brouwer, M., Courteaux, M., Ongenae, F., & Van Hoecke, S. (2023). From Lab to Real World: Assessing the Effectiveness of Human Activity Recognition and Optimization through Personalization. Sensors. https://doi.org/10.3390/s23104606

Vancouver

Stojchevska M, De Brouwer M, Courteaux M, Ongenae F, Van Hoecke S. From Lab to Real World: Assessing the Effectiveness of Human Activity Recognition and Optimization through Personalization. Sensors. 2023. doi:10.3390/s23104606

BibTeX
@article{Stojchevska2023,
  author = {Stojchevska, Marija and De Brouwer, Mathias and Courteaux, Martijn and Ongenae, Femke and Van Hoecke, Sofie},
  title = {From Lab to Real World: Assessing the Effectiveness of Human Activity Recognition and Optimization through Personalization},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23104606}
}
Kostenlos starten →