Stretchable array electromyography sensor with graph neural network for static and dynamic gestures recognition system
作者机构：Department of Advanced Materials Science and EngineeringSungkyunkwan UniversitySuwon 16419Republic of Korea Department of Electrical and Computer EngineeringSungkyunkwan UniversitySuwon 16419Republic of Korea Department of Artificial IntelligenceSungkyunkwan UniversitySuwon 16419Republic of Korea Department of Physical&Rehabilitation MedicineKangbuk Samsung HospitalSungkyunkwan University School of MedicineSeoul 03181Republic of Korea Department of Computer Science and EngineeringSungkyunkwan UniversitySuwon 16419Republic of Korea
出 版 物：《npj Flexible Electronics》 (npj-柔性电子（英文）)
年 卷 期：2023年第7卷第1期
页 面：361-373页
核心收录：
学科分类：07[理学] 0701[理学-数学] 070101[理学-基础数学]
基 金：the National Research Foundation of Korea(NRF-2022M3D1A2083618,2021R1A2B5B02002167,2021R1I1A1A01060078,and 2021R1C1C1005407) supported by the SKKU Research Fellowship Program of the Sungkyunkwan University and the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.2019-0-00421,Artificial Intelligence Graduate School Program(Sungkyunkwan University)) supported by the SafeD Inc.and BECS Inc
摘 要：With advances in artificial intelligence(AI)-based algorithms,gesture recognition accuracy from sEMG signals has continued to *** multichannel-sEMG signals substantially increase the quantity and reliability of the data for any type of ***,we report an array of bipolar stretchable sEMG electrodes with a self-attention-based graph neural network to recognize gestures with high *** array is designed to spatially cover the skeletal muscles to acquire the regional sampling data of EMG activity from 18 different *** system can differentiate individual static and dynamic gestures with~97%accuracy when training a single trial per ***,a sticky patchwork of holes adhered to an array sensor enables skin-like attributes such as stretchability and water vapor permeability and aids in delivering stable EMG *** addition,the recognition accuracy(~95%)remained unchanged even after long-term testing for over 72 h and being reused more than 10 times.
维普期刊数据库