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

Event-related potential dynamics of unilateral lower limb movement with functional connectivity analysis.

Journal of neuroscience methods·2026
Same author

Decoding imagined Chinese speech: a capsule neural network based on bidirectional knowledge transfer for hierarchical multi-label classification.

Journal of neural engineering·2026
Same author

Multi-angle phase aberration correction for holographic tomography by dual-output U-Net.

Optics express·2026
Same author

Deep learning for EEG-based sleep stage classification: a review.

Medical & biological engineering & computing·2026
Same author

Dietary capsaicin attenuates type 2 diabetes via gut microbiota and bile acid metabolic pathways.

iScience·2026
Same author

Superior efficacy and comparable safety of calcipotriol plus betamethasone dipropionate foam vs. ointment in Chinese patients with plaque psoriasis: A randomized phase 3 trial.

Chinese medical journal·2026

相关实验视频

Updated: Jun 12, 2025

Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients
06:11

Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients

Published on: April 18, 2025

276

基于适应性欧几里德对齐的轻量级无源域调整,用于脑-计算机接口.

Huiyang Wang, Hongfang Han, John Q Gan

    IEEE journal of biomedical and health informatics
    |September 18, 2024
    PubMed
    概括

    适应性欧几里德对齐 (AEA) 通过对齐主体数据分布来改善脑计算机接口 (BCI) 隐私,增强跨主体识别,而无需为每个新用户重新训练模型.

    科学领域:

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

    背景情况:

    • 基于脑电图 (EEG) 的脑电脑接口 (BCI) 需要强大的跨主题识别来保护隐私.
    • 无源域调整 (SFDA) 是有效的,但每一个新主题的更新模型是不方便的.
    • 主题之间的域偏移阻碍了主题独立的BCI的性能.

    研究的目的:

    • 提出适应性欧几里德对齐 (AEA) 来解决SFDA中的域漂移,用于跨学科的EEG分类.
    • 将AEA与现有的SFDA方法集成,以创建新的,改进的BCI模型.
    • 评估基于AEA的SFDA方法在各种EEG数据集和深度学习架构中的有效性.

    主要方法:

    • 扩展的欧几里德对齐 (EA) 提出了自适应的欧几里德对齐 (AEA),学习一个投影矩阵来对齐目标和源主体数据分布.
    • 将AEA与SHOT,GSFDA和NRC结合起来,开发了AEA-SHOT,AEA-GSFDA和AEA-NRC.
    • 将这些基于AEA的SFDA方法应用于EEGNet,Shallow ConvNet,Deep ConvNet和MSFBCNN的机动图像,ERP和SSVEP数据集.

    主要成果:

    • AEA有效地消除了域偏移,显著提高了跨主题EEG分类性能.

    更多相关视频

    Assessment and Communication for People with Disorders of Consciousness
    07:37

    Assessment and Communication for People with Disorders of Consciousness

    Published on: August 1, 2017

    9.0K
    Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring
    06:32

    Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring

    Published on: July 14, 2023

    1.2K

    相关实验视频

    Last Updated: Jun 12, 2025

    Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients
    06:11

    Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients

    Published on: April 18, 2025

    276
    Assessment and Communication for People with Disorders of Consciousness
    07:37

    Assessment and Communication for People with Disorders of Consciousness

    Published on: August 1, 2017

    9.0K
    Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring
    06:32

    Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring

    Published on: July 14, 2023

    1.2K
  • 与现有方法相比,基于AEA的SFDA方法显示出更高的性能.
  • 在PhysioNet数据集上,AEA-SHOT实现了最高的平均准确率81.4%,达到最高的平均准确率.

    • 结论:

    • 拟议的AEA是一种强大的技术,可以通过减轻域转移来增强独立于主体的BCI性能.
    • 基于AEA的SFDA方法为跨主题的EEG识别提供了实用和有效的解决方案,减少了计算负担.
    • 这些发现凸显了AEA在推进保护隐私和高性能BCI方面的潜力.