EUVIMEDEUVIMED entdecken
Crossref

Identification of Persons Based on Electrocardiogram and Motion Data

Waltenegus Dargie, Sajad Farrokhi, Christian Poellabauer

IEEE Sensors Journal · 01.07.2025 · 25 (13) · 24982-24991

DOI: 10.1109/jsen.2025.3570655 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 01.07.2025. Verfasst von Waltenegus Dargie und 2 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 20 Literaturangaben. Gefördert von: Florida Cancer Innovation Fund Award through Florida Department of Health under Grant MOAAR.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wearable sensors enable to monitor patients in their everyday environments. However, since they generate highly personal data, their protection from misuse or unauthorized use is crucial. Under certain conditions, it is important to examine whether the data they generate uniquely describe their deployment environment. This can be used to certify the authenticity of the data. In this article, we uniquely identify persons based on the measurements of a wireless electrocardiogram (ECG) and motion sensors. We let 34 subjects perform seven different activities while synchronously sampling a five-lead wireless ECG, two 3-D accelerometers, and a 3-D gyroscope. Using both time- and frequency-domain features, we train a multilayer convolutional neural network (CNN) to achieve a classification accuracy exceeding 98%. Our model is able to uniquely classify 85% of the subjects with 100% accuracy, even though more than 82% of them have similar physical constitution (they are young people between the ages of 21 and 24, with a mean age of 22 years and standard deviation of 1.9 years). The activities we consider place very different demands on the body. To demonstrate this, we perform activity recognition using the same datasets and the model classifies the activities with an average accuracy of 92%.

Förderung

  • Florida Cancer Innovation Fund Award through Florida Department of Health under Grant MOAAR

Zitieren

APA

Dargie, W., Farrokhi, S., & Poellabauer, C. (2025). Identification of Persons Based on Electrocardiogram and Motion Data. IEEE Sensors Journal, 25(13), 24982-24991. https://doi.org/10.1109/jsen.2025.3570655

Vancouver

Dargie W, Farrokhi S, Poellabauer C. Identification of Persons Based on Electrocardiogram and Motion Data. IEEE Sensors Journal. 2025;25(13):24982-24991. doi:10.1109/jsen.2025.3570655

BibTeX
@article{Dargie2025,
  author = {Dargie, Waltenegus and Farrokhi, Sajad and Poellabauer, Christian},
  title = {Identification of Persons Based on Electrocardiogram and Motion Data},
  journal = {IEEE Sensors Journal},
  year = {2025},
  volume = {25},
  number = {13},
  pages = {24982--24991},
  doi = {10.1109/jsen.2025.3570655}
}
Kostenlos starten →