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

An Interpretable Hybrid Neural Network Integrating Sinc-Convolution and Transformer for EEG-Based Depression Detection.

International journal of neural systems·2026

Same author

Dual-Action flavonol carbonized polymer dots spray: Accelerating burn wound recovery through immune responses modulation and EMT induction.

Materials today. Bio·2025

Same author

Adipose-Derived Mesenchymal Stem Cell Exosomes Encapsulating siIL1R2 Facilitate the Repair of DSS-Induced Intestinal Mucosal Injury.

Immunological investigations·2025

Same author

Development status of electrocatalytic hydrogenation of biomass small molecules and prospects for industrial production.

iScience·2025

Same author

Multilayer Brain Networks for Enhanced Decoding of Natural Hand Movements and Kinematic Parameters.

IEEE transactions on bio-medical engineering·2025

Same author

Preparation of dual-epitopes imprinted particles with γ-cyclodextrin host-guest interaction and reversible addition-fragmentation chain transfer strategy for cytochrome c collaborative recognition.

Journal of chromatography. A·2025

Search research articles

相关实验视频

Updated: Jun 25, 2025

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

跨数据集运动图像EEG转移学习的多源深域适应组合框架.

Minmin Miao^1,2, Zhong Yang¹, Zhenzhen Sheng^1,2

¹School of Information Engineering, Huzhou University, Huzhou, People's Republic of China.

Physiological measurement

|May 21, 2024

概括

这项研究引入了一种新的转移学习框架,以提高运动图像EEG分类的准确性. 拟议的多源深域适应组合框架 (MSDDAEF) 有效地解决了跨数据集的数据变化.

关键词:

交叉数据集交叉数据集深域适应的深域适应运动图像电脑电图 (EEG)多个来源的多元化.转移学习转移学习

更多相关视频

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

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

相关实验视频

Last Updated: Jun 25, 2025

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

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

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

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:

脑电图 (EEG) 对于测量大脑活动至关重要,运动图像 (MI) EEG显示出临床潜力.
卷积神经网络 (CNN) 广泛用于MI EEG分类,但性能受到特定主题数据稀缺性的限制.
缺乏特定主体数据阻碍了MIEEG分类中的解码准确性和概括性.

研究的目的:

提出一种新的转移学习 (TL) 框架,以提高MI EEG分类性能,用于使用辅助数据集的目标受试者.
开发一个多源深域适应组合框架 (MSDDAEF) 进行强大的交叉数据集MI EEG解码.
调查跨数据集TL的可行性和有效性,以改善MI EEG分类.

主要方法:

开发了一个多源深域适应组合框架 (MSDDAEF) 用于跨数据集MI EEG解码.
该MSDDAEF整合了模型预培训,深度域调整和多源组合技术.
通过检查每个组件内的不同设计来评估框架的稳定性.

主要成果:

以openBMI作为目标数据集和GIST作为源数据集实现了最高的平均分类准确率74.28%.
当GIST是目标数据集,openBMI是源数据集时,达到69.85%的平均分类准确率.
与几项已建立的研究和最先进的算法相比,证明了优越的分类性能.

结论:

交叉数据集TL是一种可行的方法,用于左/右手MIEEG解码.
在MIEEG分析中,MSDDAEF提供了一个有希望的解决方案,以减轻跨数据集的变化.
拟议的框架提高了MI EEG分类模型的准确性和通用性.