A Rapid Adaptation Approach for Dynamic Air‑Writing Recognition Using Wearable Wristbands with Self‑Supervised Contrastive Learning

作     者：Yunjian Guo Kunpeng Li Wei Yue Nam‑Young Kim Yang Li Guozhen Shen Jong‑Chul Lee Yunjian Guo;Kunpeng Li;Wei Yue;Nam-Young Kim;Yang Li;Guozhen Shen;Jong-Chul Lee

作者机构：Department of Electronic Convergence EngineeringKwangwoon UniversitySeoul 01897South Korea Radio Frequency Integrated Circuit(RFIC)Bio CentreKwangwoon UniversitySeoul 01897South Korea Department of Electronic EngineeringKwangwoon UniversitySeoul 01897South Korea School of MicroelectronicsShandong UniversityJinan 250101People’s Republic of China State Key Laboratory of Integrated Chips and SystemsFudan UniversityShanghai 200433People’s Republic of China School of Integrated Circuits and ElectronicsBeijing Institute of TechnologyBeijing 100081People’s Republic of China 

基　　金：supported by the Research Grant Fund from Kwangwoon University in 2023,the National Natural Science Foundation of China under Grant(62311540155) the Taishan Scholars Project Special Funds(tsqn202312035) the open research foundation of State Key Laboratory of Integrated Chips and Systems 

出 版 物：《Nano-Micro Letters》 (纳微快报（英文版）)

年 卷 期：2025年第17卷第2期

页      码：417-431页

摘      要：Wearable wristband systems leverage deep learning to revolutionize hand gesture recognition in daily *** existing approaches that often focus on static gestures and require extensive labeled data,the proposed wearable wristband with selfsupervised contrastive learning excels at dynamic motion tracking and adapts rapidly across multiple *** features a four-channel sensing array composed of an ionic hydrogel with hierarchical microcone structures and ultrathin flexible electrodes,resulting in high-sensitivity capacitance *** wireless transmission from a Wi-Fi module,the proposed algorithm learns latent features from the unlabeled signals of random wrist ***,only few-shot labeled data are sufficient for fine-tuning the model,enabling rapid adaptation to various *** system achieves a high accuracy of 94.9%in different scenarios,including the prediction of eight-direction commands,and air-writing of all numbers and *** proposed method facilitates smooth transitions between multiple tasks without the need for modifying the structure or undergoing extensive task-specific *** utility has been further extended to enhance human–machine interaction over digital platforms,such as game controls,calculators,and three-language login systems,offering users a natural and intuitive way of communication.

主 题 词：Wearable wristband Self-supervised contrastive learning Dynamic gesture Air-writing Human-machine interaction 

学科分类：12[管理学] 1201[管理学-管理科学与工程类] 081104[081104] 08[工学] 080203[080203] 0835[0835] 0802[工学-机械学] 0811[工学-水利类] 0812[工学-测绘类] 

核心收录：

D　O　I：10.1007/s40820-024-01545-8

馆 藏 号：203144371...