Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Identification of a Novel Glycosyltransferase Prognostic Signature in Hepatocellular Carcinoma Based on LASSO Algorithm.

Frontiers in genetics·2022
Same author

Multistimuli-Responsive Squaraine Dyad Exhibiting Concentration-Controlled Vapochromic Luminescence.

ACS applied materials & interfaces·2022
Same author

Fabrication of 3D GelMA Scaffolds Using Agarose Microgel Embedded Printing.

Micromachines·2022
Same author

Reclassification of <i>Enterobacter</i> sp. FY-07 as <i>Kosakonia oryzendophytica</i> FY-07 and Its Potential to Promote Plant Growth.

Microorganisms·2022
Same author

Three-Dimensional Microfilament Printing of a Decellularized Extracellular Matrix (dECM) Bioink Using a Microgel Printing Bath for Nerve Graft Fabrication and the Effectiveness of dECM Graft Combined with a Polycaprolactone Conduit.

ACS applied bio materials·2022
Same author

<i>In vivo</i> and <i>in vitro</i> protective effects of shengmai injection against doxorubicin-induced cardiotoxicity.

Pharmaceutical biology·2022

相关实验视频

Updated: May 13, 2025

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study
06:58

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

Published on: November 6, 2015

9.4K

一个跨用户开放式的肌电模式识别的新框架.

Ge Gao, Xu Zhang, Le Wu

    IEEE transactions on bio-medical engineering
    |April 14, 2025
    PubMed
    概括
    此摘要是机器生成的。

    本研究引入了一种用于肌电模式识别的新方法,该方法可以有效地处理不同的用户和不必要的运动. 它在识别预期的手势和拒绝异常值方面取得了很高的准确性,改善了假肢控制.

    更多相关视频

    Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
    08:15

    Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

    Published on: March 28, 2025

    300
    Structured Motor Rehabilitation After Selective Nerve Transfers
    09:34

    Structured Motor Rehabilitation After Selective Nerve Transfers

    Published on: August 15, 2019

    21.7K

    相关实验视频

    Last Updated: May 13, 2025

    A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study
    06:58

    A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

    Published on: November 6, 2015

    9.4K
    Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
    08:15

    Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

    Published on: March 28, 2025

    300
    Structured Motor Rehabilitation After Selective Nerve Transfers
    09:34

    Structured Motor Rehabilitation After Selective Nerve Transfers

    Published on: August 15, 2019

    21.7K

    科学领域:

    • 生物医学工程 生物医学工程
    • 神经科学是一个神经科学.
    • 机器学习 机器学习

    背景情况:

    • 肌电控制系统将肌肉的电活动转化为设备命令.
    • 跨用户的变化和异常运动的干扰对当前的肌电模式识别方法构成重大挑战.
    • 肌电手势接口的稳定性和可用性需要先进的模式识别技术.

    研究的目的:

    • 开发一种强大的肌电模式识别方法.
    • 为了同时减轻跨用户的变化和异常运动干扰.
    • 为了提高假肢设备的肌电控制的准确性和可靠性.

    主要方法:

    • 一个基于卷积神经网络 (CNN) 的特征提取器在现有用户数据上进行了预训练.
    • 模型转移和调整是使用新用户有限的标记数据进行的.
    • 基于欧几里得度的原型损失函数被用于改进类的分离性和紧性.
    • 通过原型匹配程序确定了内向和外向运动.

    主要成果:

    • 拟议的方法实现了82.37±1.21%的平均准确度,用于内向运动识别.
    • 该方法在异常运动拒绝方面显示了平均准确度为97.21±2.65%.
    • 在跨用户,开放式场景中,性能明显优于现有方法 (p < 0.05).

    结论:

    • 开发的方法在跨用户开放式的肌电模式识别方面表现出色.
    • 简短而简单的校准程序足以进行有效的模型调整.
    • 这项研究为改善肌电手势界面的稳定性和可用性提供了有价值的解决方案.