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

STNMAE: Identifying Spatial Domains from Spatial Transcriptomics Data with Neighbor-Aware Multi-view Masked Graph Autoencoder.

Interdisciplinary sciences, computational life sciences·2026
Same author

A Contrastive Learning-Enhanced Residual Network for Predicting Epileptic Seizures Using EEG Signals.

International journal of neural systems·2025
Same author

scRSSL: Residual semi-supervised learning with deep generative models to automatically identify cell types.

IET systems biology·2025
Same author

EEG-Based Seizure Prediction Using Hybrid DenseNet-ViT Network with Attention Fusion.

Brain sciences·2024
Same author

A review: simulation tools for genome-wide interaction studies.

Briefings in functional genomics·2024
Same author

Combining EEG Features and Convolutional Autoencoder for Neonatal Seizure Detection.

International journal of neural systems·2024

相关实验视频

Updated: Jun 7, 2025

Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization
09:57

Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization

Published on: September 20, 2024

2.5K

一个修改过的变压器网络用于使用EEG信号检测发作.

Wenrong Hu1, Juan Wang1, Feng Li1

  • 1School of Computer Science, Qufu Normal University, Rizhao 276826, P. R. China.

International journal of neural systems
|November 19, 2024
PubMed
概括

这项研究介绍了Inresformer,这是一个先进的深度学习模型,用于从脑电图 (EEG) 信号中自动检测. 该Inresformer模型显著提高了发作识别的准确性,有助于临床诊断和患者护理.

关键词:
在 Co-MixUp 上进行混合.这是一个EEGEEGEEGEEGEEGEEGEEG.离散的波形变换.发作检测检测 发作检测变压器的变压器是一个变压器.

更多相关视频

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients
09:32

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients

Published on: December 18, 2016

12.3K
Equipment Setup and Artifact Removal for Simultaneous Electroencephalogram and Functional Magnetic Resonance Imaging for Clinical Review in Epilepsy
10:23

Equipment Setup and Artifact Removal for Simultaneous Electroencephalogram and Functional Magnetic Resonance Imaging for Clinical Review in Epilepsy

Published on: June 23, 2023

1.9K

相关实验视频

Last Updated: Jun 7, 2025

Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization
09:57

Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization

Published on: September 20, 2024

2.5K
Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients
09:32

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients

Published on: December 18, 2016

12.3K
Equipment Setup and Artifact Removal for Simultaneous Electroencephalogram and Functional Magnetic Resonance Imaging for Clinical Review in Epilepsy
10:23

Equipment Setup and Artifact Removal for Simultaneous Electroencephalogram and Functional Magnetic Resonance Imaging for Clinical Review in Epilepsy

Published on: June 23, 2023

1.9K

科学领域:

  • 神经学 神经学
  • 人工智能的人工智能
  • 生物医学工程 生物医学工程

背景情况:

  • 发作严重损害了患者的身体功能和日常生活.
  • 自动发作检测对于及时的临床干预和患者管理至关重要.
  • 当前的深度学习模型在有效地从脑电图 (EEG) 信号中提取本地和全球特征方面面临挑战.

研究的目的:

  • 提出一个增强的变压器网络,Inresformer,用于改进自动发作检测.
  • 在变压器架构中利用Inception和Residual网络来实现更丰富的特征表示.
  • 增强模型的非线性表示能力,以便更准确地识别.

主要方法:

  • 使用离散波波变换 (DWT) 来将EEG信号分解成三个子频段.
  • 使用Co-MixUp方法来解决数据不平衡问题.
  • 开发了Inresformer网络,包括Inception,Residual和修改后的Feedforward层,用于发作检测.
  • 实现了基于多尺度EEG子信号的最终扣押识别的歧视性融合.

主要成果:

  • 在波恩数据集上实现了100%的准确性.
  • 在CHB-MIT数据集上达到98.03%的平均准确性.
  • 在CHB-MIT数据集中显示出高灵敏度 (95.65%) 和特异性 (98.57%).
  • 在发作检测性能方面表现优于现有的深度学习网络.

结论:

  • 该Inresformer网络提供了一个有前途的方法,用于自动检测发作.
  • 拟议的方法显示出临床研究和诊断应用的巨大潜力.
  • 增强的特征提取和非线性表示有助于竞争性的抓获识别性能.