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

Analysis of washed microbiota transplant efficacy for autism and donor-recipient gut microbiota characteristics.

Frontiers in cellular and infection microbiology·2026

Same author

Dynamic cross-linked injectable hydrogel for combined oxaliplatin-resveratrol therapy in colorectal cancer peritoneal metastasis.

Journal of nanobiotechnology·2026

Same author

Targeted Modulation of Eukaryotic Release Factor 1 (OseRF1) by an RNA Aptamer Enhances Drought Adaptation in Rice.

Plant biotechnology journal·2026

Same author

Dietary Coenzyme Q10 Supplementation Enhances Meat Quality, Nutritional Profile, and Antioxidant Status in Meat Rabbits.

Animals : an open access journal from MDPI·2026

Same author

MoS<sub>2</sub>/MoP@Ti<sub>3</sub>C<sub>2</sub>T<sub><i>x</i></sub> ternary heterostructure with dual heterointerfaces for accelerating polysulfide conversion kinetics in lithium-sulfur batteries.

Nanoscale·2026

Same author

Bound States in the Continuum Metasurfaces for Biomolecular Detection: A Review of Advances and Applications.

Advanced materials (Deerfield Beach, Fla.)·2026

Search research articles

相关实验视频

Updated: Jul 3, 2025

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Published on: May 15, 2016

MGFKD:一个半监督的多源域适应算法,用于跨主体EEG情绪识别.

Rui Zhang¹, Huifeng Guo¹, Zongxin Xu¹

¹Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology, School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, PR China.

Brain research bulletin

|February 14, 2024

概括

这项研究引入了一种用于跨主体EEG情绪识别的新算法,有效地处理负转移,使用最小的标记目标数据. 该方法显著提高了分类准确性,显示了现实世界应用的巨大潜力.

关键词:

情绪识别情绪识别黄金的主题是黄金的主题.负转移是因为负转移.半监督域适应算法半监督域适应算法转移学习转移学习

更多相关视频

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Published on: July 31, 2016

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

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

Published on: December 15, 2023

相关实验视频

Last Updated: Jul 3, 2025

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Published on: May 15, 2016

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Published on: July 31, 2016

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

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

Published on: December 15, 2023

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:

跨主体脑电图 (EEG) 情绪识别由于负转移而面临挑战.
现有的模型往往忽略了基于EEG的情绪识别中的负转移问题.
来自目标受试者的有限的标记数据阻碍了个性化情绪识别.

研究的目的:

提出一个半监督域自适应算法,MGFKD,以解决跨主体EEG情绪识别中的负转移.
从目标受试者中利用少数标记样本来提高模型性能.
提高基于EEG的情绪识别系统的效率和适用性.

主要方法:

开发了一个多域地质流动内核动态分布对齐 (MGFKD) 算法.
使用GFK常见特征提取器将源和目标主体特征投射到Grassmann多重空间.
集成了一个源域选择器来识别"黄金源主题",使用弱分类器和目标主题标签.
使用具有动态分布平衡的标签校正器来完善目标主体的伪标签.

主要成果:

在SEED和SEED-IV数据集上,MGFKD显著优于无监督和半监督域适应算法.
获得高平均准确度 (87.51±7.68%在SEED上,68.79±8.25%在SEED-IV上),每个目标受试者只有一个标记样本.
精度进一步提高到90.20±7.57% (SEED) 和69.99±7.38% (SEED-IV),使用5个标记样本和6个源域.

结论:

拟议的MGFKD算法有效地减轻了跨主体EEG情绪识别中的负面转移.
该算法表现出强大的性能,即使在新受试者的标记样本数量最小的情况下也是如此.
MGFKD对于未来基于EEG的实时情绪识别系统具有显著的应用价值.