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

A Robust Multi-Branch CNN-LSTM Architecture for Cross-Subject Motor Imagery Classification.

Sensors (Basel, Switzerland)·2026
Same author

Decoding EEG Signals for Brain-Computer Interfaces.

Studies in health technology and informatics·2026
Same author

Lightweight Sequential Transformers for Blood Glucose Level Prediction in Type-1 Diabetes.

IEEE journal of biomedical and health informatics·2025
Same author

A Systematic Literature Review of Innovations, Challenges, and Future Directions in Telemonitoring and Wearable Health Technologies.

IEEE journal of biomedical and health informatics·2025
Same author

Internet of Medical Things Systems Review: Insights into Non-Functional Factors.

Sensors (Basel, Switzerland)·2025
Same author

EEG Acquisition and Motor Imagery Classification for Robotic Control.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025

相关实验视频

Updated: Jun 23, 2025

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.3K

对于开放词汇的深度表示学习,脑电图对文字解码.

Hamza Amrani, Daniela Micucci, Paolo Napoletano

    IEEE journal of biomedical and health informatics
    |June 18, 2024
    PubMed
    概括

    这项研究引入了一种新的深度学习架构,用于使用语言模型解码脑电图 (EEG) 信号,提高脑计算机接口 (BCI) 性能和可理解性.

    科学领域:

    • 神经科学是一个神经科学.
    • 人工智能的人工智能
    • 机器学习 机器学习

    背景情况:

    • 预先训练有素的语言模型显示出通过非侵入性脑电脑接口 (BCI) 解码脑电图 (EEG) 信号的潜力.
    • 在语言模型中嵌入EEG信号和对特定主题的变异对解码性能的影响仍然不清楚.
    • 现有的BCI解码的评估指标主要是语法,缺乏对输出语义可理解性的洞察力.

    研究的目的:

    • 通过使用现代表示式学习,为开放词汇EEG解码提供端到端的深度学习架构.
    • 引入一个依赖于主题的表示学习模块,一个BART语言模型,以及一个GPT-4句子精细化模块,用于增强解码.
    • 提出基于BERTScore的综合性句子级评价指标,并进行消去研究来分析模块贡献.

    主要方法:

    • 开发了一个端到端的深度学习架构,集成了主体依赖的EEG编码,BART语言模型和GPT-4用于句子改进.
    • 使用BERTScore进行更全面的,句级评估解码输出质量.
    • 在ZuCo v1.0和v2.0数据集上评估了拟议的模型,该数据集包括30名受试者在自然阅读任务期间的EEG记录.

    主要成果:

    • 在ZuCo数据集上获得了BLEU-1分数42.75%,ROUGE-1-F分数33.28%,以及BERTScore-F分数53.86%.

    更多相关视频

    Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
    08:22

    Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

    Published on: April 26, 2024

    1.8K
    Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology
    05:38

    Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

    Published on: June 29, 2021

    2.4K

    相关实验视频

    Last Updated: Jun 23, 2025

    Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
    11:25

    Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

    Published on: July 26, 2013

    43.3K
    Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
    08:22

    Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

    Published on: April 26, 2024

    1.8K
    Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology
    05:38

    Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

    Published on: June 29, 2021

    2.4K
  • 与之前的最先进状态相比,表现有所改善,为1.40% (BLEU-1),2.59% (ROUGE-1-F) 和3.20% (BERTScore-F).
  • 一项废除研究提供了对拟议架构中每个组件的具体贡献的见解.

    • 结论:

    • 拟议的端到端深度学习架构有效解码开放词汇EEG信号,提高BCI性能.
    • 取决于主体的表示学习和GPT-4精细化模块显著有助于提高解码精度和输出可理解性.
    • 伯特斯core为BCI解码提供了一个更强大的评估指标,更好地与人类的理解保持一致.