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

Neutron dose assessment by unfolding spectra from neutron activation analysis of a smartphone.

Journal of radiological protection : official journal of the Society for Radiological Protection·2026
Same author

Heavy Metal(loid) Pollution Characteristics and Risk Assessment in the Water-Soil-Vegetable System of a Watershed in Southwest China.

Toxics·2026
Same author

A structured oral formulation database for machine learning: Uncovering data-informed design strategies to facilitate effective formulation development.

International journal of pharmaceutics·2026
Same author

The Impact of Nonthermal Pretreatment Methods on the Drying of Fruits and Vegetables.

Comprehensive reviews in food science and food safety·2026
Same author

ASCENT: an active transfer learning paradigm for efficient drug-target interaction prediction.

Science China. Life sciences·2026
Same author

ZIP10 governs Zn influx into the cytoplasm from the endoplasmic reticulum and maintains Zn homeostasis in rice.

Plant physiology·2026

相关实验视频

Updated: Jul 26, 2025

Cortical Source Analysis of High-Density EEG Recordings in Children
09:32

Cortical Source Analysis of High-Density EEG Recordings in Children

Published on: June 30, 2014

21.4K

一种基于EEG的跨数据集疲劳检测回归方法.

Duanyang Yuan1, Jingwei Yue2, Xuefeng Xiong1

  • 1Shanghai Key Laboratory of Power Station Automation, School of Mechatronics Engineering and Automation, Shanghai University, Shanghai, China.

Frontiers in physiology
|June 16, 2023
PubMed
概括

本研究引入了一种使用电脑电图 (EEG) 数据的跨数据集疲劳检测模型. 该方法有效地检测到不同数据集的疲劳,而不需要重新培训,超过现有的方法.

关键词:
这是一个EEGEEGEEGEEGEEGEEGEEG.交叉数据集交叉数据集疲劳检测 疲劳检测 疲劳检测回归方法是一种回归方法.自主监督学习学习

更多相关视频

A Method for Tracking the Time Evolution of Steady-State Evoked Potentials
12:03

A Method for Tracking the Time Evolution of Steady-State Evoked Potentials

Published on: May 25, 2019

8.5K
Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

1.9K

相关实验视频

Last Updated: Jul 26, 2025

Cortical Source Analysis of High-Density EEG Recordings in Children
09:32

Cortical Source Analysis of High-Density EEG Recordings in Children

Published on: June 30, 2014

21.4K
A Method for Tracking the Time Evolution of Steady-State Evoked Potentials
12:03

A Method for Tracking the Time Evolution of Steady-State Evoked Potentials

Published on: May 25, 2019

8.5K
Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

1.9K

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:

  • 在需要持续集中注意力的工作中,疲劳会带来重大风险.
  • 现有的基于脑电图 (EEG) 的疲劳检测模型需要大量的数据来对新数据集进行重新训练,这是不切实际的.
  • 交叉数据集疲劳检测提供了一个解决方案,但仍然在很大程度上未被研究.

研究的目的:

  • 开发一种新的基于EEG的跨数据集疲劳检测模型.
  • 为解决对新数据集进行现有模型再培训的局限性.
  • 建立适用于各种EEG数据集的疲劳检测的可靠方法.

主要方法:

  • 一种两步回归方法,涉及预训练和特定领域的适应.
  • 在预训练期间的一个借口任务是区分数据集.
  • 域调整使用共享子空间,最大平均差异 (MMD),注意力机制和门式循环单位 (GRU).

主要成果:

  • 获得了59.10%的准确性和0.27.27的根平均平方误差 (RMSE).
  • 显著超过了最先进的领域适应方法.
  • 证明高精度 (66.21%) 即使只有10%的标记样本.

结论:

  • 拟议的交叉数据集疲劳检测模型有效地将不同EEG数据集进行概括.
  • 这种方法减少了对大量数据和再培训的需求,提供了一个实际的解决方案.
  • 这项研究为未来基于EEG的深度学习研究提供了宝贵的参考.