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

The subpleural pulmonary microvasculature in newborn yak (Bos grunniens).

Veterinary research communications·2008
Same author

Experimental confirmation of potential swept source optical coherence tomography performance limitations.

Applied optics·2008
Same author

A germin-like protein gene family functions as a complex quantitative trait locus conferring broad-spectrum disease resistance in rice.

Plant physiology·2008
Same author

[Spatial and temporal changes of palatal cell proliferation and cell apoptosis of retinoic acid induced mouse cleft palate in different embryonic stages].

Hua xi kou qiang yi xue za zhi = Huaxi kouqiang yixue zazhi = West China journal of stomatology·2008
Same author

Identification of an Atlantic salmon IFN multigene cluster encoding three IFN subtypes with very different expression properties.

Developmental and comparative immunology·2008
Same author

Non-Gaussian statistics and superdiffusion in a driven-dissipative dusty plasma.

Physical review. E, Statistical, nonlinear, and soft matter physics·2008

相关实验视频

Updated: Jan 9, 2026

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

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

Published on: October 24, 2012

15.1K

SATrans-Net:基于EEG的运动图像解码的稀疏注意力变压器.

Tianhua Miao1,2, Liansen Sha1,3, Kun Huang1,3

  • 1Suzhou Institute of Biomedical Engineering and Technology,Chinese Academy of Sciences, Suzhou, 215000, Jiangsu, China.

Scientific reports
|December 4, 2025
PubMed
概括
此摘要是机器生成的。

SATrans-Net通过有效解码电脑电图 (EEG) 信号以获得运动图像 (MI) 来提高脑计算机接口 (BCI) 的准确性. 这种新的深度学习模型改进了远程依赖模型,以更好地开发辅助技术.

关键词:
大脑与计算机接口 (BCI)深度学习是一种深度学习.这是EEG-MI解码.长距离的依赖性 长距离的依赖性变压器变压器变压器

更多相关视频

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

44.0K
Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality
10:14

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

Published on: May 10, 2024

1.7K

相关实验视频

Last Updated: Jan 9, 2026

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

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

Published on: October 24, 2012

15.1K
Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

44.0K
Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality
10:14

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

Published on: May 10, 2024

1.7K

科学领域:

  • 生物医学信号处理
  • 机器学习 机器学习
  • 神经科学是一个神经科学.

背景情况:

  • 大脑-计算机接口 (BCI) 系统将电脑脑图像 (EEG) 信号解码为运动图像 (MI),以帮助运动障碍者.
  • 目前的深度学习模型与EEG-MI数据的长序列性质作斗争,限制了特征提取和解码精度.

研究的目的:

  • 引入SATrans-Net,这是一个端到端的框架,旨在模拟EEG-MI信号的远程依赖性,以提高解码性能.
  • 在BCI系统中增强特征提取和分类准确性.

主要方法:

  • 使用二维深度可分离卷积 (2D-DSC) 进行时空特征提取.
  • 在变压器架构中整合了Top-K Sparse Attention (TKSA) 机制,以高效地建模远程依赖.
  • 使用Grad-CAM用于类激活拓 (CAT) 地图生成以可视化空间注意力.

主要成果:

  • 实现了高跨会话解码精度:84.72% (BCI IV-2a),89.76% (BCI IV-2b) 和96.79% (高马).
  • 在解码准确度方面,SATrans-Net的性能优于现有的方法.
  • 废弃性研究证实了TKSA模块的显著贡献.

结论:

  • SATrans-Net 证明了对EEG-MI信号的优越解码精度和可解释性.
  • 该模型捕捉远程依赖的能力为BCI技术提供了有前途的进步.
  • 这项工作突出了计算技术在生物医学信号处理中对辅助应用的潜力.