Integration of a Lightweight Customized 2D CNN Model to an Edge Computing System for Real-Time Multiple Gesture Recognition

IF 4.3 3区材料科学 Q1 ENGINEERING, ELECTRICAL & ELECTRONIC ACS Applied Electronic Materials Pub Date : 2023-12-15 DOI:10.1007/s10723-023-09715-5

Hulin Jin, Zhiran Jin, Yong-Guk Kim, Chunyang Fan

{"title":"Integration of a Lightweight Customized 2D CNN Model to an Edge Computing System for Real-Time Multiple Gesture Recognition","authors":"Hulin Jin, Zhiran Jin, Yong-Guk Kim, Chunyang Fan","doi":"10.1007/s10723-023-09715-5","DOIUrl":null,"url":null,"abstract":"<h3>Abstract</h3> <p>The human-machine interface (HMI) collects electrophysiology signals incoming from the patient and utilizes them to operate the device. However, most applications are currently in the testing phase and are typically unavailable to everyone. Developing wearable HMI devices that are intelligent and more comfortable has been a focus of study in recent times. This work developed a portable, eight-channel electromyography (EMG) signal-based device that can distinguish 21 different types of motion. To identify the EMG signals, an analog front-end (AFE) integrated chip (IC) was created, and an integrated EMG signal acquisition device combining a stretchy wristband was made. Using the EMG movement signals of 10 volunteers, a SIAT database of 21 gestures was created. Using the SIAT dataset, a lightweight 2D CNN-LSTM model was developed and specialized training was given. The signal recognition accuracy is 96.4%, and the training process took a median of 14 min 13 s. The model may be used on lower-performance edge computing devices because of its compact size, and it is anticipated that it will eventually be applied to smartphone terminals.</p>","PeriodicalId":3,"journal":{"name":"ACS Applied Electronic Materials","volume":null,"pages":null},"PeriodicalIF":4.3000,"publicationDate":"2023-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Applied Electronic Materials","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s10723-023-09715-5","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

Abstract

The human-machine interface (HMI) collects electrophysiology signals incoming from the patient and utilizes them to operate the device. However, most applications are currently in the testing phase and are typically unavailable to everyone. Developing wearable HMI devices that are intelligent and more comfortable has been a focus of study in recent times. This work developed a portable, eight-channel electromyography (EMG) signal-based device that can distinguish 21 different types of motion. To identify the EMG signals, an analog front-end (AFE) integrated chip (IC) was created, and an integrated EMG signal acquisition device combining a stretchy wristband was made. Using the EMG movement signals of 10 volunteers, a SIAT database of 21 gestures was created. Using the SIAT dataset, a lightweight 2D CNN-LSTM model was developed and specialized training was given. The signal recognition accuracy is 96.4%, and the training process took a median of 14 min 13 s. The model may be used on lower-performance edge computing devices because of its compact size, and it is anticipated that it will eventually be applied to smartphone terminals.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

将轻量级定制 2D CNN 模型集成到边缘计算系统，用于实时多手势识别

摘要人机界面（HMI）收集来自病人的电生理信号，并利用这些信号操作设备。然而，大多数应用目前还处于测试阶段，通常无法普及。开发更智能、更舒适的可穿戴人机界面设备是近期研究的重点。这项研究开发了一种基于八通道肌电图（EMG）信号的便携式设备，可以区分 21 种不同类型的运动。为了识别肌电信号，制作了一个模拟前端（AFE）集成芯片（IC），并结合弹力腕带制作了一个集成的肌电信号采集装置。利用 10 名志愿者的肌电信号，创建了包含 21 个手势的 SIAT 数据库。利用 SIAT 数据集，开发了一个轻量级 2D CNN-LSTM 模型，并进行了专门训练。该模型由于体积小巧，可用于性能较低的边缘计算设备，预计最终将应用于智能手机终端。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊