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

Dynamic task-related prefrontal functional networks evolved in Stroop Color-Word tasks measured by fNIRS.

Cognitive neurodynamics·2026
Same author

Process Optimization of Novel Boronophenylalanine Liposomes Through Box-Behnken Response Surface Design and Preliminary Evaluation in A549 Lung Carcinoma Cells for Boron Neutron Capture Therapy.

Molecules (Basel, Switzerland)·2026
Same author

Extracellular matrix stiffness orchestrates NETs formation and mTOR-Driven metabolic reprogramming in lung cancer.

Cancer letters·2026
Same author

Lamin A/C-regulated cysteine catabolic flux modulates stem cell fate through epigenome reprogramming.

Nature metabolism·2026
Same author

Evaluating Stroke-Related Motor Impairment and Recovery Using Macroscopic and Microscopic Features of HD-sEMG.

Bioengineering (Basel, Switzerland)·2025
Same author

Wearable technologies for assisted mobility in the real world.

Nature communications·2025

相关实验视频

Updated: Jul 1, 2025

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

480

基于EMG的多用户手势分类通过无监督转移学习使用未知的校准手势.

Haojie Shi, Xinyu Jiang, Chenyun Dai

    IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society
    |March 1, 2024
    PubMed
    概括

    本研究引入了一个卷积神经网络 (CNN) 转移学习 (TL) 模型,以改进表面电肌图 (sEMG) 的手势分类. TL方法显著提高了准确性,并减少了人机交互 (HMI) 系统的校准需求.

    科学领域:

    • 生物医学工程 生物医学工程
    • 机器学习 机器学习
    • 人与计算机的交互

    背景情况:

    • 基于表面电肌图 (sEMG) 的人机交互 (HMI) 系统在一般化和培训负担方面面临挑战,阻碍了商业化.
    • 当前的sEMG手势分类模型通常需要大量的校准数据,限制了用户的可访问性.

    研究的目的:

    • 探索和比较基于卷积神经网络 (CNN) 的无监督转移学习 (TL) 算法,用于sEMG手势分类.
    • 为了减少校准数据的要求,并提高基于sEMG的HMI系统的泛化性能.

    主要方法:

    • 使用CNN的8个无监督TL算法在35个受试者的10个手势数据集上进行了评估.
    • 使用最小的校准数据,与传统分类器 (KNN,LDA,SVM,Random Forest) 进行了性能比较.

    主要成果:

    • 关联对齐 (CORAL) TL算法实现了超过90%的分类准确性,比非TL方法提高了10%.
    • 拟议的模型在最小的校准数据 (每个手势两次试验) 中超过了传统的分类器.
    • 在不同的手势 (87.94%准确率) 和几天 (84.26%准确率) 中表现出高的传输稳定性.

    结论:

    更多相关视频

    Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
    09:41

    Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

    Published on: April 21, 2023

    1.6K
    Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
    06:37

    Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

    Published on: December 15, 2023

    3.8K

    相关实验视频

    Last Updated: Jul 1, 2025

    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

    480
    Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
    09:41

    Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

    Published on: April 21, 2023

    1.6K
    Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
    06:37

    Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

    Published on: December 15, 2023

    3.8K
  • 拟议的CNN TL方法提供了一个实用的解决方案,以简化基于sEMG的HMI系统的校准过程.
  • 这种方法显著提高了手势分类的准确性,并减少了新用户的负担.
  • 无监督的TL显示了促进基于sEMG的HMI的商业可行性的巨大潜力.