EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Empirical Study of Open-Set Gesture Recognition on WiFi BVP Features

Zhenzhen Zhao, Heng Wang

Sensors · 23.10.2026 · 26 (21) · 6723

DOI: 10.3390/s26216723 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 23.10.2026. Verfasst von Zhenzhen Zhao und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer and Information Engineering (School of Software), Henan University of Economics and Law, Zhengzhou 450046, China. Hauptthemen laut MEDLINE: Gestures, Pattern Recognition, Automated. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

WiFi-based gesture recognition using domain-independent Body-coordinate Velocity Profile (BVP) features has demonstrated strong cross-domain generalization, but existing methods generally rely on closed-set assumptions, limiting their use in open-world scenarios. In this paper, we present a systematic empirical study of open-set gesture recognition on WiFi BVP features. On the CNN–GRU backbone, we evaluate seven representative OSR methods—MSP, OpenMax, Energy, ODIN, K-NN, prototype, and rejection head—under two backbone strategies (frozen and full fine-tuning), across six unknown gestures and three random seeds. Our experiments show that closed-set Softmax classifiers consistently misclassify unknown gestures with high confidence (49.7–74.3% across six gestures), and that the closed-set high-confidence misclassification rate is strongly associated with open-set AUROC (R2 = 0.918, p = 0.0026), whereas embedding-space geometric distance is not (R2 = 0.018, p = 0.80). This suggests that open-set difficulty may stem from classifier decision-boundary confusion rather than geometric separation. We further find that no single OSR method consistently outperforms all others across unknown gestures, and that frozen and fine-tuned backbones yield comparable open-set performance (typically within ±0.02 AUROC). Finally, we provide multi-objective evaluation and deployment observations, including Pareto frontiers and multiple operating points. These results offer a systematic benchmark for open-set WiFi gesture recognition and highlight the importance of classifier-level factors in determining open-set difficulty.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GesturesPattern Recognition, AutomatedHumansAlgorithmsConvolutional Neural Networks

Stichwörter der Autor:innen

Body-coordinate Velocity Profile (BVP)WiFi sensingclassifier decision boundarydomain-disjoint evaluationgesture recognitionopen-set recognition

Autor:innen und Institutionen

  • School of Computer and Information Engineering (School of Software), Henan University of Economics and Law, Zhengzhou 450046, China.
  • College of Mechanical and Electrical Engineering, Henan Agricultural University, Zhengzhou 450002, China.

Zitieren

APA

Zhao, Z., & Wang, H. (2026). An Empirical Study of Open-Set Gesture Recognition on WiFi BVP Features. Sensors, 26(21), 6723. https://doi.org/10.3390/s26216723

Vancouver

Zhao Z, Wang H. An Empirical Study of Open-Set Gesture Recognition on WiFi BVP Features. Sensors. 2026;26(21):6723. doi:10.3390/s26216723

BibTeX
@article{Zhao2026,
  author = {Zhao, Zhenzhen and Wang, Heng},
  title = {An Empirical Study of Open-Set Gesture Recognition on WiFi BVP Features},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {6723},
  doi = {10.3390/s26216723}
}
Kostenlos starten →