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

Adverse childhood friendship and depression in later life: findings from a national survey in China.

BMC psychology·2025
Same author

MSFT-transformer: a multistage fusion tabular transformer for disease prediction using metagenomic data.

Briefings in bioinformatics·2025
Same author

Bidirectional association between handgrip strength and ADLs disability: a prospective cohort study.

Frontiers in public health·2023
Same author

Glycolysis induces Th2 cell infiltration and significantly affects prognosis and immunotherapy response to lung adenocarcinoma.

Functional & integrative genomics·2023
Same author

Association between anemia and sarcopenia among Chinese elderly: A cross-sectional study based on the China health and retirement longitudinal study.

Experimental gerontology·2023
Same author

Effect of bariatric surgery on carotid intima-media thickness: A meta-analysis based on observational studies.

Frontiers in surgery·2023

相关实验视频

Updated: Jan 10, 2026

Multi-Modal Home Sleep Monitoring in Older Adults
07:40

Multi-Modal Home Sleep Monitoring in Older Adults

Published on: January 26, 2019

8.1K

睡眠混合网络:一种轻量级混合CNN-变压器模型,用于从单通道EEG中增强N1睡眠分期.

Hao Zhou, Mengxiang Su, Jeng-Shyang Pan

    IEEE journal of biomedical and health informatics
    |November 24, 2025
    PubMed
    概括

    SleepHybridNet是一种新的深度学习模型,使用脑电图 (EEG) 信号准确地分类非快速眼动睡眠阶段1 (N1) 睡眠. 这种轻量级的混合CNN-变压器方法改善了临床应用的N1睡眠检测.

    科学领域:

    • 神经科学是一个神经科学.
    • 人工智能的人工智能
    • 生物医学工程 生物医学工程

    背景情况:

    • 准确识别非快速眼动第1阶段 (N1) 睡眠对于睡眠神经科学和临床实践至关重要.
    • 目前的深度学习模型在N1睡眠分类中面临挑战,因为信号特征含糊不清.

    研究的目的:

    • 介绍SleepHybridNet,一种轻量级的混合卷积神经网络 (CNN) - 变压器模型,用于增强N1睡眠阶段分类.
    • 使用单通道电脑电图 (EEG) 信号提高睡眠阶段分类的准确性和概括能力.

    主要方法:

    • 开发了SleepHybridNet,集成了一个多尺度卷积神经网络 (MSCNN) 模块和一个变压器编码器.
    • 在新型架构中包含了光谱特征提取和多任务分类器.
    • 使用公开可用的Sleep-EDF扩展数据集进行模型培训和验证.

    主要成果:

    • 睡眠混合网络的整体准确率为88.2%,N1睡眠阶段分类的F1得分为0.633.
    • 证明了卓越的性能,特别是在代表性不足的N1和N3睡眠阶段,优于现有的方法.
    • 该模型的轻量级设计 (5.1M参数) 便于在临床环境中进行实际部署.

    结论:

    更多相关视频

    Optogenetic Manipulation of Neural Circuits During Monitoring Sleep/wakefulness States in Mice
    08:58

    Optogenetic Manipulation of Neural Circuits During Monitoring Sleep/wakefulness States in Mice

    Published on: June 19, 2019

    10.4K
    Simultaneous Electroencephalography, Real-time Measurement of Lactate Concentration and Optogenetic Manipulation of Neuronal Activity in the Rodent Cerebral Cortex
    10:45

    Simultaneous Electroencephalography, Real-time Measurement of Lactate Concentration and Optogenetic Manipulation of Neuronal Activity in the Rodent Cerebral Cortex

    Published on: December 19, 2012

    20.7K

    相关实验视频

    Last Updated: Jan 10, 2026

    Multi-Modal Home Sleep Monitoring in Older Adults
    07:40

    Multi-Modal Home Sleep Monitoring in Older Adults

    Published on: January 26, 2019

    8.1K
    Optogenetic Manipulation of Neural Circuits During Monitoring Sleep/wakefulness States in Mice
    08:58

    Optogenetic Manipulation of Neural Circuits During Monitoring Sleep/wakefulness States in Mice

    Published on: June 19, 2019

    10.4K
    Simultaneous Electroencephalography, Real-time Measurement of Lactate Concentration and Optogenetic Manipulation of Neuronal Activity in the Rodent Cerebral Cortex
    10:45

    Simultaneous Electroencephalography, Real-time Measurement of Lactate Concentration and Optogenetic Manipulation of Neuronal Activity in the Rodent Cerebral Cortex

    Published on: December 19, 2012

    20.7K
    • 睡眠混合网络提供了一个有前途的解决方案,用于从单通道EEG准确和高效的N1睡眠阶段分类.
    • 该模型的性能和轻量级性质弥合了先进的深度学习和睡眠医学中的临床适用性之间的差距.
    • 未来的研究可能涉及将可穿戴传感器的多式联络数据集成到更广泛的应用中.