Behavioral Gait Biometrics in VR: Is the Use of Synthetic Samples Able to Increase Person Identification Metrics?
Computer Animation and Virtual Worlds · 2025-03 · 36 (2)
DOI: 10.1002/cav.70016 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Animation and Virtual Worlds, online erschienen am 10.04.2025. Verfasst von Aleksander Sawicki. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 25 Literaturangaben. Gefördert von: Narodowe Centrum Nauki.
Abstract (Originalsprache)
In this paper, we present an approach to build a biometric system capable of identifying subjects based on gait. The experiments were carried out with a proprietary gait corpus collected from 100 subjects. In the data acquisition process, we used a commercially available perception neuron body suit equipped with motion sensors and dedicated to entertainment in the VR domain. Classification was performed using two variants of the CNN architecture and evaluated using cross‐day validation. A novelty in the presented approach was the exploration of research areas related to the usage of synthetically generated samples. Experiments were conducted for two types of preprocessing—a low‐pass filtering of the signals using a 3rd‐ or 1st‐order Butterworth filter. For the first variant, the synthetic samples generated by the long short‐term memory‐mixture density network (LSTM‐MDN) model allowed us to increase the F1‐score from 0.928 to 0.966. Meanwhile, in the second case from 0.970 to 0.978 F1‐score.
Förderung
- Narodowe Centrum Nauki
Zitieren
APA
Sawicki, A. (2025). Behavioral Gait Biometrics in VR: Is the Use of Synthetic Samples Able to Increase Person Identification Metrics?. Computer Animation and Virtual Worlds, 36(2). https://doi.org/10.1002/cav.70016
Vancouver
Sawicki A. Behavioral Gait Biometrics in VR: Is the Use of Synthetic Samples Able to Increase Person Identification Metrics?. Computer Animation and Virtual Worlds. 2025;36(2). doi:10.1002/cav.70016
BibTeX
@article{Sawicki2025,
author = {Sawicki, Aleksander},
title = {Behavioral Gait Biometrics in VR: Is the Use of Synthetic Samples Able to Increase Person Identification Metrics?},
journal = {Computer Animation and Virtual Worlds},
year = {2025},
volume = {36},
number = {2},
doi = {10.1002/cav.70016}
}
EUVIMED