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

Glycine as a Metabolic Regulator of Reproductive Function in Livestock: From Gametes to Early Embryos.

Animals : an open access journal from MDPI·2026
Same author

Vertical Heterojunction Nanowire-Based Ambient-Stable γ-CsPbI<sub>3</sub> Self-Powered Photodetectors with Enhanced Performance for Photoplethysmography.

Nano letters·2026
Same author

Applications of Dynamic Polymers in Next-Generation High-Performance Lithium-Based Batteries.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

A pH-responsive vanillin-Schiff base microcapsule for controlled release of pyraclostrobin.

Pest management science·2026
Same author

Ultrasound-Activatable Piezoelectric Hydrogel Reprograms Mitochondrial Epigenetics for Osteoarthritis Therapy via the mTOR/GATD3A Axis.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Case Report: ERAT-based management of appendiceal abscess in early pregnancy.

Frontiers in surgery·2026

相关实验视频

Updated: Jul 26, 2025

Recording Horizontal Saccade Performances Accurately in Neurological Patients Using Electro-oculogram
06:12

Recording Horizontal Saccade Performances Accurately in Neurological Patients Using Electro-oculogram

Published on: March 13, 2018

10.7K

基于Tiny U-Net的单通道EEG和EOG的睡眠阶段.

Jingyi Lu1, Chang Yan1, Jianqing Li1

  • 1State Key Laboratory of Bioelectronics, School of Instrument Science and Engineering, Southeast University, 210096, Nanjing, China.

Computers in biology and medicine
|June 13, 2023
PubMed
概括

TinyUStaging是一种使用单线EEG和EOG的自动睡眠分阶段模型,在各种数据集中表现出强大的泛化. 它实现了高精度和稳定性,改善了少数睡眠阶段的识别,特别是在OSA患者中.

科学领域:

  • 生物医学工程 生物医学工程
  • 睡眠医学 睡眠医学
  • 人工智能的人工智能

背景情况:

  • 目前的睡眠分期算法缺乏一般化,限制了实际应用.
  • 不同质的数据集对于开发强大的睡眠分析工具至关重要.
  • 解决阶级不平衡对于准确的睡眠阶段分类至关重要,特别是对于像N1.1这样的少数阶段.

研究的目的:

  • 开发一种轻量级,可通用的自动睡眠分期架构 (TinyUStaging).
  • 改进少数和难以分类的睡眠阶段 (N1,N3) 的识别,特别是在OSA患者中.
  • 在大规模,不平衡和异质睡眠数据上验证模型的性能.

主要方法:

  • 使用了七个异质睡眠数据集 (9970条记录,20k+小时,7226名受试者).
  • 开发了TinyUStaging,这是一个U-Net架构,具有通道和空间联合注意 (CSJA) 和挤压和激发 (SE) 块.
  • 实施了概率补偿抽样策略和一个类意识的稀重子和焦点 (SWDF) 损失函数.

主要成果:

  • 在异质数据集上,平均整体准确率为84.62%,宏F1得分 (MF1) 为79.6%,卡帕为0.764.
  • 证明了卓越的性能,特别是在N1分类中,优于现有方法.
关键词:
注意U-Net的注意事项不平衡的大数据失衡单导电源的EEG电流是单导电源的.一个单一的领导者EOG.睡眠分期是指睡眠的分期.

更多相关视频

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography
06:40

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography

Published on: June 15, 2018

10.2K
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

43.4K

相关实验视频

Last Updated: Jul 26, 2025

Recording Horizontal Saccade Performances Accurately in Neurological Patients Using Electro-oculogram
06:12

Recording Horizontal Saccade Performances Accurately in Neurological Patients Using Electro-oculogram

Published on: March 13, 2018

10.7K
Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography
06:40

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography

Published on: June 15, 2018

10.2K
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

43.4K
  • 展示了模型稳定性,整体MF1标准偏差在0.175以内,跨越交叉验证折叠.

    • 结论:

    • TinyUStaging提供了一种可靠和可通用的解决方案,用于使用单导电脑电脑电图和电脑电图的自动睡眠阶段.
    • 该模型为有效的医院外睡眠监测提供了基础,即使数据不平衡和多样化.
    • 提出的方法有效地解决了类不平衡,并提高了关键睡眠阶段的分类准确性.