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

Cardiac health assessment across scenarios and devices using a multimodal foundation model pretrained on data from 1.7 million individuals.

Nature machine intelligence·2026

Same author

Digital Phenotyping for Adolescent Mental Health: Feasibility Study Using Machine Learning to Predict Mental Health Risk From Active and Passive Smartphone Data.

Journal of medical Internet research·2026

Same author

Speaker-independent dysarthria severity classification using self-supervised transformers and multi-task learning.

PLOS digital health·2025

Same author

Transforming label-efficient decoding of healthcare wearables with self-supervised learning and "embedded" medical domain expertise.

Communications engineering·2025

Same author

Safety of human-AI cooperative decision-making within intensive care: A physical simulation study.

PLOS digital health·2025

Same author

The 'Sandwich' meta-framework for architecture agnostic deep privacy-preserving transfer learning for non-invasive brainwave decoding.

Journal of neural engineering·2024

Search research articles

相关实验视频

Updated: Jul 11, 2025

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

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

Published on: July 26, 2013

用转移学习图形神经网络对具有异质电极配置的数据集进行EEG解码.

Jinpei Han¹, Xiaoxi Wei¹, A Aldo Faisal^1,2

¹Brain & Behaviour Lab, Department of Computing, Imperial College London, London SW7 2AZ, United Kingdom.

Journal of neural engineering

|November 6, 2023

概括

本研究引入了一种新的机器学习框架,使用图形神经网络和转移学习来提高脑机界面 (BMI) 的准确性. 该方法有效地结合了多样化的脑电图 (EEG) 数据集,克服了不同电极布局的挑战,以更好地分类运动图像.

关键词:

这是EEG信号.大脑-计算机接口接口域名适应域名适应图表神经网络的神经网络不同质的数据集.运动图像图像学转移学习转移学习

更多相关视频

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

High-density Electroencephalographic Acquisition in a Rodent Model Using Low-cost and Open-source Resources

High-density Electroencephalographic Acquisition in a Rodent Model Using Low-cost and Open-source Resources

Published on: November 26, 2016

相关实验视频

Last Updated: Jul 11, 2025

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

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

Published on: July 26, 2013

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

High-density Electroencephalographic Acquisition in a Rodent Model Using Low-cost and Open-source Resources

High-density Electroencephalographic Acquisition in a Rodent Model Using Low-cost and Open-source Resources

Published on: November 26, 2016

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:

脑机界面 (BMI) 依赖于机器学习来提取特征,需要大量的数据集.
由于记录设备和电极布局的变化,结合不同的数据集是具有挑战性的,导致数据分布的转移.

研究的目的:

开发一个机器学习框架,克服BMI的领域适应挑战.
为了使不同电极配置和实验协议的不同数据集的学习.

主要方法:

开发了一个结合图形神经网络 (GNN) 和转移学习的新型框架.
这种方法应用于非侵入性运动图像 (MI) 电脑图像 (EEG) 解码.
使用了三个MIEEG数据库,具有不同的电极号码 (22-64) 和布局.

主要成果:

基于GNN的转移学习框架在测试数据集上实现了高精度和低标准偏差.
该模型有效地从具有不同电极布局的数据集中汇总了知识.
观察到独立于主体的MIEEG分类有了更好的概括性.

结论:

拟议的框架通过整合各种EEG数据集,有效地解决了BMI中的域调整问题.
这种方法提高了运动图像分类的概括能力,克服了非统一的实验设置的局限性.
这些发现推动了大脑与计算机接口技术的开发和应用.