Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Lymph node metastasis-related circHELQ promotes progression and acts as a nanotherapeutic target in colorectal cancer.

Journal of nanobiotechnology·2026

Same author

Preoperative topical 5% benzoyl peroxide reduces intraoperative deep cutibacterium acnes contamination in shoulder arthroscopy: a retrospective cohort study.

BMC surgery·2026

Same author

Exercise mimetics: molecular mechanisms, biological and therapeutic effects.

Molecular biomedicine·2026

Same author

Study on the effectiveness and safety of balance instrument training on balance and lower limb motor function in patients with ischemic stroke hemiplegia.

Frontiers in rehabilitation sciences·2026

Same author

Mechanochemical NH<sub>4</sub>Cl-mediated hydrogen-bonding network reconstruction of HFIP: enabling yne-allylic substitutions.

Chemical communications (Cambridge, England)·2026

Same author

Fluorescence and colorimetric dual-signal sensing of resveratrol and ascorbic acid based on NaYF₄:Yb,Er@NaYF₄ upconversion nanoparticles.

Mikrochimica acta·2026

Search research articles

相关实验视频

Updated: Sep 19, 2025

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Published on: May 10, 2024

TCANet:一个时间卷积注意力网络用于运动图像EEG解码.

Wei Zhao¹, Haodong Lu¹, Baocan Zhang¹

¹Chengyi College, Jimei University, Xiamen, 361021 China.

Cognitive neurodynamics

|June 17, 2025

概括

这项研究介绍了TCANet,这是一个用于解码运动图像脑电图 (MI-EEG) 信号的新型模型,显著改善了脑计算机接口 (BCI) 的性能. TCANet有效地捕捉复杂的时空模式,在主题依赖的任务中表现优于现有的方法.

关键词:

大脑与计算机接口 (BCI)深度学习 (DL) 是指深度学习.运动图像 (MI)专注于自己的注意力时间卷积网络 (TCN)

更多相关视频

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients

Published on: September 1, 2023

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

相关实验视频

Last Updated: Sep 19, 2025

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Published on: May 10, 2024

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients

Published on: September 1, 2023

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

科学领域:

神经科学是一个神经科学.
生物医学工程生物医学工程
信号处理信号处理

背景情况:

解码运动图像脑电图 (MI-EEG) 信号对于大脑与计算机接口 (BCI) 的发展至关重要.
在BCI中存在的挑战来自MI-EEG信号的固有复杂性和可变性,阻碍了强大的解码.
现有的模型往往难以有效地捕捉MI-EEG数据中的复杂的时空动态.

研究的目的:

提出TCANet,一个新的端到端时间卷积注意力网络,旨在从MI-EEG信号中进行层次的时空特征提取.
为了提高MI-EEG解码的准确性和稳定性,用于BCI应用.
评估TCANet在主体依赖和主体独立的场景中与已建立的基线对比的表现.

主要方法:

TCANet采用多尺度卷积模块来提取各种分辨率的局部时空表示.
一个时间卷积模块融合和压缩这些特征,模拟短期和长期依赖关系.
一个堆叠的多头自我注意力机制完善了全球表示,然后是一个完全连接的层,用于MI-EEG分类.

主要成果:

在BCI IV-2a和IV-2b数据集的受试者依赖分类中,TCANet的准确率分别为83.06%和88.52%,卡帕值为0.7742和0.7703.
在依赖对象的MI-EEG解码中,TCANet的表现优于几个代表性的基线模型.
该模型在IV-2a数据集上的具有挑战性的独立主体设置中显示出具有竞争力的性能,这表明IV-2b的进一步改进潜力.

结论:

通过其集成的卷积和注意力机制,TCANet通过分层捕捉时空依赖性来有效地解码MI-EEG信号.
拟议的模型在BCI技术中提供了显著的进步,特别是在主题依赖的MI-EEG分类任务中.
进一步的研究可以探索TCANet对主题独立的BCI应用程序的适应性和性能增强.