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

Effects of Environmental Arsenic Exposure on the Morphology of Multiple Organs in Female Mice During Pre-Pregnancy, Gestation, and Lactation.

Journal of applied toxicology : JAT·2026
Same author

Association of 24-Hour Computed Tomography Infarct Density on Functional Outcomes in Stroke: Secondary Analysis From the AcT Trial.

Journal of the American Heart Association·2026
Same author

Research on gut microbiota and metabolic characteristics in patients with sleep disorders after ischemic stroke.

Metabolic brain disease·2026
Same author

Age-adjustment of the combined early ischemic change and collateral extent score for outcomes after endovascular therapy.

AJNR. American journal of neuroradiology·2026
Same author

Intracranial Hemorrhage Patterns and Outcomes in Minor Stroke: Analysis of the TEMPO-2 Trial.

Stroke·2026
Same author

LAE-Net: Large Pretrained Models Assistant Text-Guided Image Editing Adversarial Network.

IEEE transactions on visualization and computer graphics·2026

相关实验视频

Updated: Jan 12, 2026

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

5.2K

SFT-HN:用于基于EEG的情绪识别的新型空间频率时间混合网络.

Lei Zhu1, Yu Ding1, Aiai Hung1

  • 1School of Automation, Hangzhou Dianzi University, Hangzhou, 310000 China.

Cognitive neurodynamics
|November 7, 2025
PubMed
概括

这项研究引入了一种新的空间-频率-时间混合网络 (SFT-HN),用于先进的脑电图 (EEG) 情绪识别. SFT-HN模型有效地融合了EEG空间,频率和时间信息,在情绪分类任务中实现了高准确性.

关键词:
深度学习是一种深度学习.不同的热量差异.这是一个EEGEEGEEGEEGEEGEEGEEG.情绪识别 情绪识别

更多相关视频

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
08:31

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

Published on: July 31, 2016

14.4K
Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
05:51

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

Published on: May 15, 2016

9.4K

相关实验视频

Last Updated: Jan 12, 2026

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

5.2K
Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
08:31

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

Published on: July 31, 2016

14.4K
Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
05:51

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

Published on: May 15, 2016

9.4K

科学领域:

  • 神经科学是一个神经科学.
  • 人工智能的人工智能
  • 信号处理 信号处理

背景情况:

  • 脑电图 (EEG) 情绪识别对于脑电脑接口 (BCI) 至关重要.
  • 深度学习方法在EEG情绪识别中优于传统技术.
  • 在融合空间,频率和时间EEG信息以及利用歧视性局部模式方面仍然存在挑战.

研究的目的:

  • 提出一种新的混合模型,即空间-频率-时间混合网络 (SFT-HN),用于增强EEG情绪识别.
  • 为了有效地融合来自EEG信号的空间,频率和时间信息.
  • 为了提高情绪分类,利用歧视性的本地模式来提高情绪分类.

主要方法:

  • 开发了一个空间-频率-时间混合网络 (SFT-HN),结合了空间频率剩余模块 (SFRM) 和基于注意力的双向长期短期记忆 (ATBI-LSTM).
  • 利用原始EEG信号的4D表示来保存空间,频率和时间信息.
  • 在SFRM中采用分割转换合并技术,残余和注意力机制用于空间频率特征提取.
  • 在ATBI-LSTM中整合了注意力机制,以捕捉时间依赖.

主要成果:

  • 在DEAP数据集上实现了97.61% (激发) 和97.57% (价值) 的平均准确性.
  • 在SEED数据集上获得了97.44%的平均准确性.
  • 在新的FACED数据集上,证明了强大的概括,平均准确率为96.24%.

结论:

  • SFT-HN模型有效地整合了空间,频率和时间EEG特征,以实现卓越的情绪识别.
  • 拟议的模型在多个数据集中展示了高准确性和强大的概括性.
  • SFT-HN为BCI提供了基于EEG的情绪识别方面的有希望的进步.