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 potential acute and chronic toxicity of cyfluthrin on the soil model organism, Eisenia fetida.

Ecotoxicology and environmental safety·2017
Same author

Ameliorative effect of vitamin E on hepatic oxidative stress and hypoimmunity induced by high-fat diet in turbot (Scophthalmus maximus).

Fish & shellfish immunology·2017
Same author

Percutaneous Vascular Interventions Versus Bypass Surgeries in Patients With Critical Limb Ischemia: A Comprehensive Meta-analysis.

Annals of surgery·2017
Same author

Silymarin protects against renal injury through normalization of lipid metabolism and mitochondrial biogenesis in high fat-fed mice.

Free radical biology & medicine·2017
Same author

Effect of complications on oncologic outcomes after pancreaticoduodenectomy for pancreatic cancer.

The Journal of surgical research·2017
Same author

Effect of crowding stress on the immune response in turbot (Scophthalmus maximus) vaccinated with attenuated Edwardsiella tarda.

Fish & shellfish immunology·2017

相关实验视频

Updated: Jul 21, 2025

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

14.7K

一个时间依赖学习CNN与注意力 MI-EEG解码机制的机制.

Xinzhi Ma, Weihai Chen, Zhongcai Pei

    IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society
    |July 27, 2023
    PubMed
    概括

    这项研究引入了一种新的深度学习模型,用于运动图像大脑-计算机接口,通过有效捕捉大脑活动的时间依赖,显著改善电脑学信号解码. 这种新方法提高了脑电脑接口应用程序的准确性.

    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:

    • 基于运动图像 (MI) 的脑电脑接口 (BCI) 系统利用脑电图 (EEG) 信号来解码大脑活动.
    • 当前的深度学习方法往往忽略了与心脏病相关的EEG模式中的关键时间依赖性,从而限制了解码性能.
    • 对特定学科的BCI开发需要对MI任务中的时间动态进行强有力的学习.

    研究的目的:

    • 提出一种新的时间依赖学习卷积神经网络 (CNN),具有用于增强MI-EEG解码的注意力机制.
    • 解决现有方法的局限性,以捕捉MI相关模式在不同任务阶段之间的时间关系.
    • 提高基于MI的BCI系统的准确性和稳定性.

    主要方法:

    • 一个CNN架构结合一个空间卷积块,从多视图EEG数据中学习空间和光谱特征.
    • 将EEG数据细分为非重叠的时间窗口,以从不同MI阶段提取区分特征.
    • 实施一个时间关注模块,在时间窗口中权衡和融合特征,捕捉时间依赖.

    主要成果:

    • 拟议的网络在BCI竞争IV-2a (BCIC-IV-2a) 数据集上实现了79.48%的平均准确性,比现有方法提高了2.30%.
    • 在BCIC-IV-2a和OpenBMI数据集上,与最先进的算法相比,表现出更高的性能.

    更多相关视频

    Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients
    07:43

    Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

    Published on: June 17, 2019

    7.8K
    Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
    12:09

    Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

    Published on: August 5, 2014

    18.1K

    相关实验视频

    Last Updated: Jul 21, 2025

    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

    14.7K
    Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients
    07:43

    Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

    Published on: June 17, 2019

    7.8K
    Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
    12:09

    Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

    Published on: August 5, 2014

    18.1K
  • 验证了学习时间依赖的有效性,以改善MI-EEG解码.

    • 结论:

    • 新的时间依赖学习CNN与注意力机制显著提高MI-EEG解码性能.
    • 捕捉时间依赖性对于开发高性能,对象特定的基于MI的BCI至关重要.
    • 拟议的方法为解码复杂的大脑信号的BCI技术提供了有希望的进步.