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

Efficacy of higher-dose versus lower-dose corticosteroids in community-acquired pneumonia: a systematic review and network meta-analysis.

Critical care (London, England)·2026
Same author

Machine Learning-Assisted Nanopore for Enhanced Fingerprinting Analysis of Functional Glycans.

Analytical chemistry·2026
Same author

TRABD2A promotes osteogenic differentiation of human periodontal ligament stem cells by modulating TNF-α and IL-1β.

Organogenesis·2026
Same author

Correlation between tissue temperature and ablation interval time under ultra-high-power short-duration ablation: Ex vivo porcine model.

Journal of interventional cardiac electrophysiology : an international journal of arrhythmias and pacing·2026
Same author

A Blood-Derived Double-Network Hydrogel with Robust Wet Adhesion for Keratinized Mucosa Regeneration via Neutrophil Phenotype Reprogramming and Mechanophysical Niche Modulation.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Carbon nanotube fiber electrode-based implantable electroacupuncture ameliorates myocardial ischemia in rats via the FXR/SHP pathway.

Nanotechnology·2026

相关实验视频

Updated: May 22, 2025

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

2.5K

基于注意力图卷积和变压器的多模式抑郁检测.

Xiaowen Jia1, Jingxia Chen1, Kexin Liu1

  • 1College of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi'an, Shaanxi, China.

Mathematical biosciences and engineering : MBE
|March 14, 2025
PubMed
概括
此摘要是机器生成的。

这项研究引入了一种新的多式联络深度学习模型,用于使用脑电图 (EEG) 和语音信号检测抑郁症. 通过有效地融合复杂的大脑和语音数据,MHA-GCN_ViT模型显著提高了准确性.

关键词:
电脑电流信号 电脑电流信号在决策层面的核聚变.图表 卷积网络 卷积网络多头注意力多头注意力多模式抑郁症 多模式抑郁症语言信号 语音信号 语音信号

更多相关视频

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
05:19

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

2.1K
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

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

Published on: October 24, 2012

14.6K

相关实验视频

Last Updated: May 22, 2025

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

2.5K
Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
05:19

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

2.1K
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

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

Published on: October 24, 2012

14.6K

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:

  • 单模压力检测方法由于个体变化和噪声而面临局限性.
  • 现有的多式联络方法在电脑电图 (EEG) 和语音信号的有效特征融合方面扎.

研究的目的:

  • 开发和评估一种多模式抑郁症检测模型,MHA-GCN_ViT,集成EEG和语音数据.
  • 通过先进的深度学习技术,提高抑郁症检测的准确性和稳定性.

主要方法:

  • 利用离散波波变换 (DWT) 进行EEG特征提取和图形卷积网络 (GCN) 用多头注意力进行大脑网络分析.
  • 采用短时间的里埃变换器 (STFT) 和视觉变换器 (ViT) 来处理来自EEG和语音信号的光谱特征.
  • 在最终低谷分类的决策层面上融合了提取的特征.

主要成果:

  • MHA-GCN_ViT模型实现了高性能指标:89.03%的准确率,90.16%的精度,89.04%的回忆率和88.83%的F1评分在MODMA数据集上.
  • 与传统的单模式方法相比,显示出显著的改进.
  • 显示强大的性能和广泛适用于多式联运检测任务.

结论:

  • 拟议的MHA-GCN_ViT模型为多式联络抑郁症检测提供了一种强大而有效的方法.
  • 这种方法在使用结合EEG和语音数据诊断心理和神经障碍方面表现有前途.