EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Eye-Rubbing Detection Using a Smartwatch: A Feasibility Study Demonstrated High Accuracy With Machine Learning

Sina Elahi, Tom Mery, Christophe Panthier, Alain Saad, Damien Gatinel, Alexandre Alahi

Translational Vision Science & Technology · 2024

DOI: 10.1167/tvst.13.9.1 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Translational Vision Science & Technology, 2024. Verfasst von Sina Elahi und 5 weiteren Autor:innen. Beteiligte Einrichtung: Fondation Ophtalmologique Adolphe de Rothschild, Rue Manin, Paris, France. Hauptthemen laut MEDLINE: Machine Learning, Feasibility Studies, Wearable Electronic Devices. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

In this work, we present a new machine learning method based on the transformer neural network to detect eye rubbing using a smartwatch in a real-life setting. In ophthalmology, the accurate detection and prevention of eye rubbing could reduce incidence and progression of ectasic disorders, such as keratoconus, and to prevent blindness.

Methods

Our approach leverages the state-of-the-art capabilities of the transformer network, widely recognized for its success in the field of natural language processing (NLP). We evaluate our method against several baselines using a newly collected dataset, which consist of data from smartwatch sensors associated with various hand-face interactions.

Results

The current algorithm achieves an eye-rubbing detection accuracy greater than 80% with minimal (20 minutes) and up to 97% with moderate (3 hours) user-specific fine-tuning.

Conclusions

This research contributes to advancing eye-rubbing detection and establishes the groundwork for further studies in hand-face interactions monitoring using smartwatches. Translational Relevance: This experiment is a proof-of-concept that eye-rubbing detection is effectively detectable and distinguishable from other similar hand gestures, solely through a wrist-worn device and could lead to further studies and patient education in keratoconus management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningFeasibility StudiesWearable Electronic DevicesHumansAlgorithmsNeural Networks, ComputerBlinking

Autor:innen und Institutionen

  • Fondation Ophtalmologique Adolphe de Rothschild, Rue Manin, Paris, France.
  • Visual Intelligence for Transportation, Ecole Polytechnique Fédérale de Lausanne, Route Cantonale, Lausanne, Switzerland.
  • Université Internationale Abulcassis des Sciences de Santé, Rabat, Morocco.

Zitieren

APA

Elahi, S., Mery, T., Panthier, C., Saad, A., Gatinel, D., & Alahi, A. (2024). Eye-Rubbing Detection Using a Smartwatch: A Feasibility Study Demonstrated High Accuracy With Machine Learning. Translational Vision Science & Technology. https://doi.org/10.1167/tvst.13.9.1

Vancouver

Elahi S, Mery T, Panthier C, Saad A, Gatinel D, Alahi A. Eye-Rubbing Detection Using a Smartwatch: A Feasibility Study Demonstrated High Accuracy With Machine Learning. Translational Vision Science & Technology. 2024. doi:10.1167/tvst.13.9.1

BibTeX
@article{Elahi2024,
  author = {Elahi, Sina and Mery, Tom and Panthier, Christophe and Saad, Alain and Gatinel, Damien and Alahi, Alexandre},
  title = {Eye-Rubbing Detection Using a Smartwatch: A Feasibility Study Demonstrated High Accuracy With Machine Learning},
  journal = {Translational Vision Science & Technology},
  year = {2024},
  doi = {10.1167/tvst.13.9.1}
}
Kostenlos starten →