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

相关实验视频

Updated: Jul 11, 2025

fMRI Validation of fNIRS Measurements During a Naturalistic Task
10:36

fMRI Validation of fNIRS Measurements During a Naturalistic Task

Published on: June 15, 2015

20.9K

重新思考fNIRS分类的延迟血液动力学反应

Zenghui Wang, Jihong Fang, Jun Zhang

    IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society
    |November 7, 2023
    PubMed
    概括
    此摘要是机器生成的。

    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

    Mental health outcomes and rehabilitation challenges in children with orthopedic trauma: a public health survey from a pediatric rehabilitation center.

    Frontiers in public health·2025
    Same author

    Protective role of cooked rice modified with complex enzymes on chronic disease in mice.

    Food chemistry·2025
    Same author

    The causal relationship between gut microbiota and lower extremity deep vein thrombosis combined with pulmonary embolism.

    Frontiers in microbiology·2024
    Same author

    Progress in clinical treatment and nursing of pediatric eosinophilic esophagitis.

    Minerva medica·2023
    Same author

    Deep learning-guided postoperative pain assessment in children.

    Pain·2023
    Same author

    Application of deep-learning-based artificial intelligence in acetabular index measurement.

    Frontiers in pediatrics·2023

    一个新的模型,fNIRSNet,通过将血液动力学延迟的领域知识纳入功能近红外光谱 (fNIRS) 信号分类来提高脑计算机接口 (BCI) 的性能. 这种高效的模型的性能优于现有的深度学习方法,降低了实际BCI应用的计算成本.

    科学领域:

    • 神经成像是一种神经成像.
    • 生物医学工程 生物医学工程
    • 机器学习 机器学习

    背景情况:

    • 功能近红外光谱 (fNIRS) 是一种非侵入性神经成像技术.
    • 改善fNIRS信号分类对于推进脑计算机接口 (BCI) 至关重要.
    • 当前的深度神经网络 (DNN) 经常忽视fNIRS血液动力学反应的固有延迟,导致性能限制.

    研究的目的:

    • 引入一个新的,高效的深度学习模型,fNIRSNet,用于fNIRS信号分类.
    • 将延迟血液动力学反应的领域知识集成到模型架构中.
    • 提高基于fNIRS的BCI的性能和实用性.

    主要方法:

    • 开发了fNIRSNet,一个简洁的深度学习模型,将延迟的血液动力学反应纳入知识领域.
    • 在卷积层中利用了内核大小和受体场的考虑.
    • 为fNIRSNet.Net建立了三个经验设计准则.
    • 在开放式访问数据集上使用特定主体和主体独立的实验设计来评估模型.

    主要成果:

    • 与其他DNN相比,fNIRSNet在基准fNIRS数据集上表现出优越的分类性能.
    • 在心理算术任务中,fNIRSNet的准确度比CNN的准确度高6.58%,具有数百万个参数,尽管只有498个参数.

    更多相关视频

    Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels
    08:19

    Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

    Published on: October 20, 2023

    1.1K
    Deep Brain Stimulation with Simultaneous fMRI in Rodents
    11:09

    Deep Brain Stimulation with Simultaneous fMRI in Rodents

    Published on: February 15, 2014

    14.1K

    相关实验视频

    Last Updated: Jul 11, 2025

    fMRI Validation of fNIRS Measurements During a Naturalistic Task
    10:36

    fMRI Validation of fNIRS Measurements During a Naturalistic Task

    Published on: June 15, 2015

    20.9K
    Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels
    08:19

    Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

    Published on: October 20, 2023

    1.1K
    Deep Brain Stimulation with Simultaneous fMRI in Rodents
    11:09

    Deep Brain Stimulation with Simultaneous fMRI in Rodents

    Published on: February 15, 2014

    14.1K
  • fNIRSNet的浮点运算 (FLOP) 比传统的CNN要低得多.

    • 结论:

    • fNIRSNet为fNIRS信号分类提供了一种高效有效的方法,其性能优于现有的DNN.
    • 该模型的降低参数数量和计算负载使其适合于实际的,低成本的BCI应用.
    • 这种以知识为导向的方法有可能激发进一步的研究,开发先进的fNIRS BCI.