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

PMSN: A Parallel Multi-Compartment Spiking Neuron for Multiscale Temporal Processing.

IEEE transactions on neural networks and learning systems·2026

Same author

Maternal cold exposure improves offspring metabolic health via a milk lithocholic acid-microbiota-Th17 axis.

NPJ biofilms and microbiomes·2026

Same author

Advances in intraoperative margin assessment for solid tumors: Toward a new era of personalized precision surgery.

European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology·2026

Same author

Straw Return and Tillage Regulate Soil N Pool via Modifying Soil Conditions and Bacterial Communities in Coastal Saline-Alkaline Land.

Microorganisms·2026

Same author

Exopolysaccharide-rosmarinic acid complex as a phosphate replacer: dual improvement of oxidative stability and gel properties in myofibrillar proteins.

Food chemistry: X·2026

Same author

Correction: Research on curing reaction kinetics and curing process of hydroxy-terminated polybutadiene (HTPB) propellants.

Scientific reports·2026

Search research articles

相关实验视频

Updated: Feb 24, 2026

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

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

Published on: June 27, 2013

MSGM:一个多尺度的时空图形Mamba用于EEG情感识别.

Hanwen Liu¹, Yifeng Gong¹, Zuwei Yan²

¹The School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen, China.

Frontiers in neuroscience

|February 23, 2026

概括

多尺度时空图马巴 (MSGM) 通过高效地建模大脑动态来增强脑电图 (EEG) 情绪识别. 这种新的方法实现了移动健康应用的高精度和实时性能.

关键词:

马姆巴·马姆巴是什么意思电脑电图 (EEG) 是一个电脑电图.情感识别情感识别情感识别图形神经网络是一个神经网络.多个尺度的多个尺度.

更多相关视频

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

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: Feb 24, 2026

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

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

Published on: June 27, 2013

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

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

科学领域:

神经科学是一个神经科学.
计算机科学计算机科学
人工智能的人工智能

背景情况:

基于脑电图 (EEG) 的情绪识别对于移动健康和情感计算至关重要.
现有的方法在复杂的大脑动态建模和边缘部署的计算效率之间的权衡中扎.
当前的方法往往忽视了多层次的时间动态和层次的空间大脑连接.

研究的目的:

引入多尺度时空图马巴 (MSGM) 以实现高效,强大的基于EEG的情感识别.
解决现有方法中复杂的时空大脑活动和计算开销的建模方面的局限性.
通过边缘部署AI来促进实时临床监测和情感互动.

主要方法:

拟议的MSGM使用多窗口时间细分来进行相对功率光谱密度 (rPSD) 特性提取.
采用双模全球和局部图形,通过多深度图形卷积网络 (GCNs) 改进,以建模层次大脑连接.
集成了一个单层的MSST-Mamba模块,用于线性计算复杂性和高效的状态空间建模.

主要成果:

在主题独立的协议下,MSGM在SEED,THU-EP和FACED数据集中实现了竞争性的准确性和F1分数 (例如,在SEED上83.43%的准确性).
在NVIDIA Jetson Xavier NX边缘设备上演示了毫秒级推理 (151 ms),证实了实时适用性.
由于单一的MSST-Mamba层架构,展示了强大的泛化和效率.

结论:

MSGM有效地捕捉复杂的时空大脑动态,具有较低的计算开销,适合实时应用.
该框架将神经解剖学先验集成到状态空间建模中,以提高准确性和可解释性.
未来的工作将重点放在多式联运一体化和优化层次空间建模,以实现跨主题的可变性.