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

Neutrophil-to-lymphocyte ratio is associated with diabetic peripheral neuropathy in type 2 diabetes patients.

Diabetes research and clinical practice·2017
Same author

Genetic variation and phylogeographic structure of the cotton aphid, Aphis gossypii, based on mitochondrial DNA and microsatellite markers.

Scientific reports·2017
Same author

Tetramethylpyrazine blocks TFAM degradation and up-regulates mitochondrial DNA copy number by interacting with TFAM.

Bioscience reports·2017
Same author

Mitochondrial LON protease-dependent degradation of cytochrome c oxidase subunits under hypoxia and myocardial ischemia.

Biochimica et biophysica acta. Bioenergetics·2017
Same author

The efficacy and safety of epinephrine for postoperative bleeding in total joint arthroplasty: A PRISMA-compliant meta-analysis.

Medicine·2017
Same author

The correlation between histological gastritis staging- 'OLGA/OLGIM' and serum pepsinogen test in assessment of gastric atrophy/intestinal metaplasia in China.

Scandinavian journal of gastroenterology·2017

相关实验视频

Updated: Jan 14, 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

15.2K

因果驱动的卷积多重注意网络用于脑电图信号解码.

Bin Lu, Junxiang Chen, Fuwang Wang

    IEEE transactions on pattern analysis and machine intelligence
    |October 27, 2025
    PubMed
    概括
    此摘要是机器生成的。

    一个新的因果关系驱动网络 (CD-CMAN) 通过从脑电图 (EEG) 信号中学习不变表示来改进脑电脑接口 (BCI),提高在分布外情景中的性能.

    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
    A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
    11:14

    A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

    Published on: October 4, 2015

    11.4K

    相关实验视频

    Last Updated: Jan 14, 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

    15.2K
    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
    A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
    11:14

    A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

    Published on: October 4, 2015

    11.4K

    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:

    • 深度学习方法在脑计算机接口 (BCI) 中取得了成功.
    • 由于假设独立且相同分布 (i.i.d) 的假设,BCI面临着与分布外 (OOD) 数据的挑战. 数据. 数据. 数据.
    • 现有的模型在现实世界的BCI应用中难以通用.

    研究的目的:

    • 提出一种新的因果驱动的卷积式多重注意网络 (CD-CMAN).
    • 增强用于BCI的电脑电图 (EEG) 信号处理中的分布外 (OOD) 通用化.
    • 学习对数据变异具有稳健性的不变表示.

    主要方法:

    • 一个时空卷积模块从EEG信号中提取特征.
    • 具有多重注意力的双隐藏编码器将特征分为语义和变化因子.
    • 因果建模,里曼的几何学和信息理论 (HSIC) 强制执行潜伏因素的独立性和信息性.

    主要成果:

    • 与两个公共数据集的基线方法相比,CD-CMAN在两个公共数据集上显示出更高的性能.
    • 该模型在主体依赖和主体独立的设置中都显示出一致的改进.
    • 学习的不变表示显著增强了OOD概括能力.

    结论:

    • 拟议的CD-CMAN为改善BCI泛化提供了一个强大的解决方案.
    • 基于因果关系的方法可以有效地解决i.i.d. 对于BCI,深度学习中的假设限制.
    • 这项工作为更可靠,更实用的BCI应用铺平了道路.