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

Emotion Recognition Using Multi-View EEG-fNIRS and Cross-Attention Feature Fusion.

Biosensors·2026
Same author

Emotion Recognition Based on a EEG-fNIRS Hybrid Brain Network in the Source Space.

Brain sciences·2025
Same author

EEG-fNIRS-Based Emotion Recognition Using Graph Convolution and Capsule Attention Network.

Brain sciences·2024
Same author

High-Emissivity Double-Layer ZrB<sub>2</sub>-Modified Coating on Flexible Aluminum Silicate Fiber Fabric with Enhanced Oxidation Resistance and Tensile Strength.

Materials (Basel, Switzerland)·2024
Same author

<i>PpSAUR5</i> promotes plant growth by regulating lignin and hormone pathways.

Frontiers in plant science·2024
Same author

Inhibiting dissolution strategy achieving high-performance sodium titanium phosphate hybrid anode in seawater-based dual-ion battery.

Journal of colloid and interface science·2024

相关实验视频

Updated: Feb 28, 2026

Correlating Behavioral Responses to fMRI Signals from Human Prefrontal Cortex: Examining Cognitive Processes Using Task Analysis
10:33

Correlating Behavioral Responses to fMRI Signals from Human Prefrontal Cortex: Examining Cognitive Processes Using Task Analysis

Published on: June 20, 2012

13.3K

基于注意力图的EEG-fNIRS交叉主体情绪识别同型网络和对比学习.

Bingzhen Yu1, Xueying Zhang1, Guijun Chen1

  • 1College of Electronic Information Engineering, Taiyuan University of Technology, Taiyuan 030024, China.

Brain sciences
|February 27, 2026
PubMed
概括

这项研究介绍了DC-AGIN,这是一种新的双对比学习网络,用于使用脑电图 (EEG) 和功能近红外光谱 (fNIRS) 改进情绪识别. 该方法增强了跨学科的概括性,以实现更强大的情感计算.

科学领域:

  • 神经科学是一个神经科学.
  • 情感计算是一种情感计算.
  • 机器学习 机器学习

背景情况:

  • 脑电图 (EEG) 和功能近红外光谱 (fNIRS) 捕捉大脑动态,以识别情绪.
  • 结合EEG和fNIRS显得有前途,但由于信号异质性和主体间变异性,在多模式融合和跨主体概括方面面临挑战.

研究的目的:

  • 为基于EEG-fNIRS的情感识别开发一种强大的方法,克服跨模态融合和跨主体概括的局限性.
  • 介绍DC-AGIN,一个双对比学习注意力图形同型网络,旨在提高情绪识别准确性和概括性.

主要方法:

  • 拟议的DC-AGIN模型使用注意力加权的图形同态网络 (AGIN) 编码器进行适应性特征强调.
  • 实现跨模态对比学习以在共享的语义空间中对齐EEG和fNIRS表示.
  • 员工监督对比学习,以减少对象特定的信息,并促进对象不变的情感表现.

主要成果:

  • 在主体依赖的四类情绪分类中,获得了96.98%的准确性.
  • 在LOSO (Leave-one-subject-out) 协议下,通过62.56%的准确度,证明了显著的跨主题概括性.
  • 超越了现有的模型,在EEG-fNIRS情感识别中实现了最先进的 (SOTA) 性能.
关键词:
这是一个EEGEEGEEGEEGEEG.相反的学习学习学习.情感识别 情感识别 情感识别在FNIRS中使用.图形异态网络的图形同型.

更多相关视频

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

34.4K
Conducting Concurrent Electroencephalography and Functional Near-Infrared Spectroscopy Recordings with a Flanker Task
13:18

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

Published on: May 24, 2020

8.3K

相关实验视频

Last Updated: Feb 28, 2026

Correlating Behavioral Responses to fMRI Signals from Human Prefrontal Cortex: Examining Cognitive Processes Using Task Analysis
10:33

Correlating Behavioral Responses to fMRI Signals from Human Prefrontal Cortex: Examining Cognitive Processes Using Task Analysis

Published on: June 20, 2012

13.3K
Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

34.4K
Conducting Concurrent Electroencephalography and Functional Near-Infrared Spectroscopy Recordings with a Flanker Task
13:18

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

Published on: May 24, 2020

8.3K

结论:

  • 注意聚合,交叉模式和交叉主体对比学习显著提高了EEG-fNIRS情绪识别的稳定性.
  • DC-AGIN模型有效地学习了可概括的情感表示,证明了它对现实世界情感计算应用的潜力.