Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline

Journals

Article Types

Countries / Regions

remove_circle_outline

Search Results (1)

Search Parameters:
Keywords = Kolmogrov–Arnold network

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
25 pages, 16941 KB  
Article
KAN-Sense: Keypad Input Recognition via CSI Feature Clustering and KAN-Based Classifier
by Minseok Koo and Jaesung Park
Electronics 2025, 14(15), 2965; https://doi.org/10.3390/electronics14152965 - 24 Jul 2025
Viewed by 347
Abstract
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 [...] Read more.
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. Full article
Show Figures

Figure 1

Back to TopTop