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

The Dual Roles of Autophagy in Important Picornaviruses Infecting Livestock and Poultry.

Veterinary sciences·2026
Same author

A Comprehensive Visual Detection Strategy: Versatile LAMP Assay with Phenol Red and Lateral Flow Dipstick for On-Site Detection of <i>Riemerella anatipestifer</i>.

Microorganisms·2026
Same author

A novel polyadenylation signal variant NM_000517.6 (<i>HBA2</i>): c.*92_*97delinsTA causing α-thalassemia in two Chinese families.

Frontiers in medicine·2026
Same author

LYVE-1 identifies asthma and drives PDGF-BB-induced proliferation, migration, and oxidative stress in airway smooth muscle cells via the PI3K/Akt pathway.

Frontiers in pharmacology·2026
Same author

Electrochemiluminescence Biosensor Based on Dual-Signal Regulation of Gold Nanoclusters for Amyloid-β Protein Detection.

Analytical chemistry·2026
Same author

COSOS-1k: A Benchmark Dataset and Occlusion-Aware Uncertainty Learning for Multi-View Video Object Detection.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

相关实验视频

Updated: Jun 20, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

515

通过自我监督的三重网络学习可解释的大脑功能连接,以深度智慧的注意力.

Yunbo Tang, Weirong Huang, Rongchang Liu

    IEEE journal of biomedical and health informatics
    |July 19, 2024
    PubMed
    概括

    这项研究介绍了TripletNet-DA,这是一种新的自我监督深度学习模型,用于生成可解释的大脑功能连接. 它使用EEG数据有效地歧视自闭症谱系障碍和严重抑郁症.

    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:

    • 传统的大脑功能连接分析面临着确定性模型和经验分析的局限性.
    • 深度学习方法通常优先考虑状态分类,而不是可解释的连接特性.

    研究的目的:

    • 提出一个自我监督的三重网络,以深度为重点 (TripletNet-DA),以产生可解释的功能连接.
    • 提高深度学习模型在捕捉功能连接动态方面的能力.

    主要方法:

    • 使用通道智能转换来增强时间数据,以创建相关和非相关的样本对,用于自我监督的训练.
    • 采用卷积网络通道编码器和相似度估计器来提取深度特征并生成功能连接表示.
    • 应用三位数损失与负相似性惩罚,以最大限度地减少非相关的样本对的相似性,增强学习.

    主要成果:

    • 与最先进的方法相比,TripletNet-DA在自闭症谱系障碍 (ASD) 歧视和严重抑郁症 (MDD) 分类方面表现优异.
    • 使用特定的EEG频段实现了ASD (高达98.32%) 和MDD (高达91.80%) 分类的高准确率.
    • 确定了ASD和典型发展个体之间的显著功能连接差异,与经验发现保持一致.

    更多相关视频

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    384
    Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
    06:37

    Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

    Published on: December 15, 2023

    2.7K

    相关实验视频

    Last Updated: Jun 20, 2025

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    515
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    384
    Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
    06:37

    Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

    Published on: December 15, 2023

    2.7K

    结论:

    • TripletNet-DA提供了一种强大的方法,可以从EEG数据中生成可解释的功能连接.
    • 该模型显示了作为神经和精神疾病如ASD和MDD的临床分析生物标志物的潜力.
    • 这种方法促进了深度学习与神经科学的整合,以了解大脑动态.