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

Electroencephalogram Monitoring in Critical Care: Multicenter Analysis of Timing, Duration, and Readmissions.

Critical care explorations·2026

Same author

Crystalline lens geometry from a clinical OCT-based biometer in pre-cataract surgery patients.

Research square·2026

Same author

Automated estimation of frequency and spatial extent of periodic and rhythmic epileptiform activity from continuous electroencephalography data.

Journal of neural engineering·2025

Same author

LG-Sleep: Local and Global Temporal Dependencies for Mice Sleep Scoring.

IEEE sensors letters·2025

Same author

A Machine Learning Approach for Identifying People With Neuroinfectious Diseases in Electronic Health Records: Algorithm Development and Validation.

JMIR medical informatics·2025

Same author

Automated estimation of frequency and spatial extent of periodic and rhythmic epileptiform activity from continuous electroencephalography data.

medRxiv : the preprint server for health sciences·2025

Search research articles

相关实验视频

Updated: May 24, 2025

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

基于EEG的强大的情绪识别,使用初始和双面扰乱模型.

Shadi Sartipi, Mujdat Cetin

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference

|March 5, 2025

概括

这项研究引入了一种新的Inception特征生成器和双面扰动 (INC-TSP) 方法,以改进来自电脑电图 (EEG) 信号的自动情绪识别,增强对噪音和攻击的稳定性.

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:

使用脑电图 (EEG) 信号的自动情绪识别对于脑电脑接口至关重要.
基于EEG的情绪识别深度学习模型易受环境噪音和对抗攻击的影响.
提高对输入扰动的模型弹性对于可靠的情绪识别至关重要.

研究的目的:

提出和验证Inception特征生成器和双面扰动 (INC-TSP) 方法,以实现基于EEG的强大的情绪识别.
提高深度学习模型在对抗攻击和输入不确定性方面的弹性.
为了应对在杂或被操纵的EEG数据中保持精确情绪识别的挑战.

主要方法:

开发了一种INC-TSP方法,集成了用于EEG特征提取的Inception模块.
实施双边扰动 (TSP) 来引入模型权重和输入的最坏情况扰动.
在一个独立于主体的三类情绪识别任务中验证了这种方法.

主要成果:

INC-TSP方法在独立于主体的情绪识别方面表现强.
拟议的方法增强了模型的弹性,可以抵御对抗性攻击和输入干扰.
尽管输入不确定性,但仍然保持了准确的情绪识别.

更多相关视频

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

相关实验视频

Last Updated: May 24, 2025

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

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

结论:

INC-TSP方法为增强基于EEG的情绪识别系统的稳定性提供了一个有希望的解决方案.
这种方法有效地减轻了噪音和对抗性攻击对深度学习模型的影响.
这些发现支持开发更可靠,更安全的脑电脑接口.