EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

KAN-Sense: Keypad Input Recognition via CSI Feature Clustering and KAN-Based Classifier

Minseok Koo, Jaesung Park

Electronics · 24.07.2025 · 14 (15) · 2965

DOI: 10.3390/electronics14152965 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 24.07.2025. Verfasst von Minseok Koo und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Institute for Advancement of Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wi-Fi sensing leverages variations in CSI (channel state information) to infer human activities in a contactless and low-cost manner, with growing applications in smart homes, healthcare, and security. While deep learning has advanced macro-motion sensing tasks, micro-motion sensing such as keypad stroke recognition remains underexplored due to subtle inter-class CSI variations and significant intra-class variance. These challenges make it difficult for existing deep learning models typically relying on fully connected MLPs to accurately recognize keypad inputs. To address the issue, we propose a novel approach that combines a discriminative feature extractor with a Kolmogorov–Arnold Network (KAN)-based classifier. The combined model is trained to reduce intra-class variability by clustering features around class-specific centers. The KAN classifier learns nonlinear spline functions to efficiently delineate the complex decision boundaries between different keypad inputs with fewer parameters. To validate our method, we collect a CSI dataset with low-cost Wi-Fi devices (ESP8266 and Raspberry Pi 4) in a real-world keypad sensing environment. Experimental results verify the effectiveness and practicality of our method for keypad input sensing applications in that it outperforms existing approaches in sensing accuracy while requiring fewer parameters.

Förderung

  • Korea Institute for Advancement of Technology

Zitieren

APA

Koo, M., & Park, J. (2025). KAN-Sense: Keypad Input Recognition via CSI Feature Clustering and KAN-Based Classifier. Electronics, 14(15), 2965. https://doi.org/10.3390/electronics14152965

Vancouver

Koo M, Park J. KAN-Sense: Keypad Input Recognition via CSI Feature Clustering and KAN-Based Classifier. Electronics. 2025;14(15):2965. doi:10.3390/electronics14152965

BibTeX
@article{Koo2025,
  author = {Koo, Minseok and Park, Jaesung},
  title = {KAN-Sense: Keypad Input Recognition via CSI Feature Clustering and KAN-Based Classifier},
  journal = {Electronics},
  year = {2025},
  volume = {14},
  number = {15},
  pages = {2965},
  doi = {10.3390/electronics14152965}
}
Kostenlos starten →