Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Establishing a Multimodal Model for Predicting Lymphovascular Invasion in Breast Cancer Using Deep Transfer Learning Based on Ultrasound and Dynamic Contrast-Enhanced Magnetic Resonance Imaging.

Oncology research and treatment·2026

Same author

Endogenous metabolite signaling orchestrates tumor immune evasion.

Cell insight·2026

Same author

Theoretical design of self-assembled hole transport materials based on π-conjugation engineering for inverted perovskite solar cells.

Physical chemistry chemical physics : PCCP·2026

Same author

Water Quality Impacts of Legacy Ion-Adsorption Rare Earth Element Mining and Processing.

Environmental science & technology·2026

Same author

Emotion recognition using spectral-spatial attention multi-temporal scale network: EEG study.

Brain informatics·2026

Same author

Pediococcus acidilactici PA53 Improves Emotional Well-Being and Gut Health While Modulating Microbiota Composition in Older Adults: A Randomized, Double-Blind, Placebo-Controlled Trial.

The Journal of nutrition·2026

Search research articles

相关实验视频

Updated: Feb 28, 2026

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

为混合EEG-fNIRS认知任务分类解双向时空融合网络.

Zirui Wang¹, Guanghao Huang¹, Zhuochao Chen¹

¹Institute for Future, School of Automation, Qingdao University, Qingdao 266071, China.

|February 27, 2026

概括

这项研究介绍了BiSTF-Net,这是一种用于融合脑电图 (EEG) 和功能近红外光谱 (fNIRS) 信号的新方法. 这种新方法显著提高了使用多式神经成像的认知任务识别精度.

关键词:

这是一个EEGEEGEEGEEGEEGEEGEEG.认知任务分类认知任务分类解的核聚变是分离的在FNIRS中使用.多式神经成像多式神经成像时空对齐的空间时间对齐

更多相关视频

Conducting Concurrent Electroencephalography and Functional Near-Infrared Spectroscopy Recordings with a Flanker Task

Conducting Concurrent Electroencephalography and Functional Near-Infrared Spectroscopy Recordings with a Flanker Task

Published on: May 24, 2020

Inter-Brain Synchrony in Open-Ended Collaborative Learning: An fNIRS-Hyperscanning Study

Inter-Brain Synchrony in Open-Ended Collaborative Learning: An fNIRS-Hyperscanning Study

Published on: July 21, 2021

相关实验视频

Last Updated: Feb 28, 2026

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

Conducting Concurrent Electroencephalography and Functional Near-Infrared Spectroscopy Recordings with a Flanker Task

Conducting Concurrent Electroencephalography and Functional Near-Infrared Spectroscopy Recordings with a Flanker Task

Published on: May 24, 2020

Inter-Brain Synchrony in Open-Ended Collaborative Learning: An fNIRS-Hyperscanning Study

Inter-Brain Synchrony in Open-Ended Collaborative Learning: An fNIRS-Hyperscanning Study

Published on: July 21, 2021

科学领域:

神经成像是一种神经成像.
认知神经科学认知神经科学
生物医学工程生物医学工程

背景情况:

多模式神经成像,集成脑电图 (EEG) 和功能近红外光谱 (fNIRS),对于大脑功能研究至关重要.
在EEG和fNIRS信号之间存在显著的时空异质性,这给有效的数据融合带来了挑战.
认知任务识别需要强大的方法来结合不同的神经数据流.

研究的目的:

介绍BiSTF-Net,一种用于增强认知任务识别的新型深度学习架构.
解决融合异质EEG和fNIRS信号的挑战,以提高分类准确度.
开发一个强大的和可解释的解决方案,用于多式联络神经成像数据分析.

主要方法:

实现了一个BiSTF-Net架构,具有分离的,双向的时空融合.
利用双向交叉模式指导 (Bi-CMG) 来实现EEG和fNIRS之间的空间特征的相互增强.
采用自适应时间对齐 (ATA) 进行fNIRS信号延迟的数据驱动对齐,以及对称交叉注意力融合 (SCAF) 进行深度特征融合.

主要成果:

BiSTF-Net实现了高平均准确率:83.33%的心理算术 (MA),82.09%的运动图像 (MI) 和84.99%的词生成 (WG).
与认知任务分类中的现有技术相比,提出的方法显示出更高的性能.
融合策略导致了神经活动的模式不变和歧视性表示.

结论:

BiSTF-Net为多式EEG-fNIRS认知任务分类提供了一种优越,稳健和可解释的方法.
该方法为未来的多式联运数据融合和临床应用研究提供了坚实的基础.
时空融合机制有效地解决了EEG和fNIRS信号的异质性.