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

Isolation of the YB strain of canine distemper virus from Yanbian, China: analysis of JAK2-STAT3 signaling and NLRP3 inflammasome activation in infected cells.

The Journal of veterinary medical science·2026

Same author

First Isolation of Bovine Coronavirus From Yanbian, China, and Analytical Validation of a SYBR Green I RT-qPCR Panel for Calf Diarrhea Viruses.

Transboundary and emerging diseases·2026

Same author

Neu1 inhibition restrains BCoV replication and modulates ZBP1-dependent PANoptosis.

Veterinary research·2026

Same author

In-Plane Mechanical Behavior Design of a Locally Rib-Reinforced Rotating Hexagonal Honeycomb.

Biomimetics (Basel, Switzerland)·2026

Same author

Crashworthiness Analysis of Bio-Inspired Multi-Cell Concave Tubes.

Biomimetics (Basel, Switzerland)·2026

Same author

Intercellular Communication-Driven Mitochondrial Transfer via CXCR4-Engineered Macrophages Reprograms Bone Marrow Metabolism for Osteoporosis Therapy.

Advanced materials (Deerfield Beach, Fla.)·2026

Search research articles

相关实验视频

Updated: Jun 7, 2025

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

一个基于自我注意的类对齐网络,用于跨主题的EEG分类.

Sufan Ma¹, Dongxiao Zhang¹, Jiayi Wang¹

¹School of Science, Jimei University, Xiamen, People's Republic of China.

Biomedical physics & engineering express

|November 11, 2024

概括

本研究引入了一种新的对抗性学习模型,通过对各个学科的特征进行对齐,同时保持阶级区别,来改进脑电图 (EEG) 的分类. 该方法通过利用来自多个个体的数据来增强特定对象的EEG分析.

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:

电脑电图 (EEG) 信号的变化需要特定对象的模型.
对于EEG而言,现有的域调整方法专注于域调整,可能忽略了关键的类界限.
这可能导致分类任务中的特征类别相关性较弱.

研究的目的:

提出一种新的对抗性学习模型,以加强特定学科的EEG分类.
利用来自多个受试者的信息来改进个人EEG分析.
通过专注于域调整和类分离性来解决当前域调整策略的局限性.

主要方法:

从EEG信号中提取浅层和注意力驱动的深层特征.
采用带有新歧视损失函数的类区分器来对齐相同类的特征,并在各域之间分离不同的类特征.
使用两个并行,协调的分类器进行联合决策.

主要成果:

拟议的模型有效地利用多个主体的数据来增强个人EEG分类.
反对策略成功地将各个领域的特征协调一致,同时保持类可分离性.
在两个公共EEG数据集上的实验验证证明了该模型的卓越有效性.

关键词:

在EEG分类中,EEA的分类.阶级对齐阶级对齐这是一个跨主题的跨主题.运动图像图像学自己注意力自我注意力

更多相关视频

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

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

相关实验视频

Last Updated: Jun 7, 2025

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

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

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

结论:

新的对抗式学习方法显著改善了特定学科的EEG分类.
该方法有效地平衡了域调整和类歧视,以实现强大的特征提取.
这项工作为开发更准确,更可靠的EEG分析工具提供了有希望的方向.