EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Behavioral Biometrics in VR: Changing Sensor Signal Modalities

Aleksander Sawicki iD, Khalid Saeed, Wojciech Walendziuk iD

Sensors · 2025

DOI: 10.3390/s25185899 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Aleksander Sawicki und 2 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Computer Science, University of Technology, 15-351 Bialystok, Poland. Hauptthemen laut MEDLINE: Virtual Reality, Biometry, Biometric Identification. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Centre, Ministry of Science and Higher Education in Poland, the Ministry of Science and Higher Education in Poland.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid evolution of virtual reality systems and the broader metaverse landscape has prompted growing research interest in biometric authentication methods for user verification. These solutions offer an additional layer of access control that surpasses traditional password-based approaches by leveraging unique physiological or behavioral traits. Current literature emphasizes analyzing controller position and orientation data, which presents challenges when using convolutional neural networks (CNNs) with non-continuous Euler angles. The novelty of the presented approach is that it addresses this limitation. We propose a modality transformation approach that generates acceleration and angular velocity signals from trajectory and orientation data. Specifically, our work employs algebraic techniques—including quaternion algebra—to model these dynamic signals. Both the original and transformed data were then used to train various CNN architectures, including Vanilla CNNs, attention-enhanced CNNs, and Multi-Input CNNs. The proposed modification yielded significant performance improvements across all datasets. Specifically, F1-score accuracy increased from 0.80 to 0.82 for the Comos subset, from 0.77 to 0.82 for the Quest subset, and notably from 0.83 to 0.92 for the Vive subset.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Virtual RealityBiometryBiometric IdentificationHumansNeural Networks, ComputerAlgorithms

Stichwörter der Autor:innen

CNNVRbiometricsdeep learningquaternionvirtual reality

Autor:innen und Institutionen

  • Faculty of Computer Science, University of Technology, 15-351 Bialystok, Poland.
  • Department of Computer Science and Electronics, Universidad de la Costa, Barranquilla 080002, Colombia.
  • Faculty of Electrical Engineering, University of Technology, 15-351 Bialystok, Poland.

ORCID-Profile: Aleksander Sawicki, Wojciech Walendziuk

Förderung

  • National Science Centre
  • Ministry of Science and Higher Education in Poland
  • the Ministry of Science and Higher Education in Poland

Zitieren

APA

Sawicki, A., Saeed, K., & Walendziuk, W. (2025). Behavioral Biometrics in VR: Changing Sensor Signal Modalities. Sensors. https://doi.org/10.3390/s25185899

Vancouver

Sawicki A, Saeed K, Walendziuk W. Behavioral Biometrics in VR: Changing Sensor Signal Modalities. Sensors. 2025. doi:10.3390/s25185899

BibTeX
@article{Sawicki2025,
  author = {Sawicki, Aleksander and Saeed, Khalid and Walendziuk, Wojciech},
  title = {Behavioral Biometrics in VR: Changing Sensor Signal Modalities},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25185899}
}
Kostenlos starten →