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

Unipolar and Bipolar Depression Detection and Classification Based on Actigraphic Registration of Motor Activity Using Machine Learning and Uniform Manifold Approximation and Projection Methods.

Diagnostics (Basel, Switzerland)·2023

Same author

Dementia Detection from Speech Using Machine Learning and Deep Learning Architectures.

Sensors (Basel, Switzerland)·2022

Same author

An Analytical Study of Speech Pathology Detection Based on MFCC and Deep Neural Networks.

Computational and mathematical methods in medicine·2022

Same author

Sign Language Recognition for Arabic Alphabets Using Transfer Learning Technique.

Computational intelligence and neuroscience·2022

Same author

Deep Transfer Learning Approaches in Performance Analysis of Brain Tumor Classification Using MRI Images.

Journal of healthcare engineering·2022

Same author

Convolution-Based Encoding of Depth Images for Transfer Learning in RGB-D Scene Classification.

Sensors (Basel, Switzerland)·2021

Search research articles

相关实验视频

Updated: Jun 6, 2025

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

从EEG数据中解码想象中的语音:一种混合深度学习方法来捕获空间和时间特征.

Yasser F Alharbi¹, Yousef A Alotaibi¹

¹Computer Engineering Department, King Saud University, Riyadh 11451, Saudi Arabia.

Life (Basel, Switzerland)

|November 27, 2024

概括

这项研究引入了一种新的深度学习方法来分析脑电图 (EEG) 数据,通过捕捉时空大脑活动来改善想象中的英语单词的识别. 这种方法实现了77.8%的准确性,增强了大脑与计算机接口的能力.

科学领域:

神经成像是一种神经成像.
认知神经科学认知神经科学
机器学习机器学习

背景情况:

电脑电图 (EEG) 提供高时间分辨率,但对大脑活动分析的空间分辨率有限.
整合空间和时间EEG数据以识别心理活动是一个重大挑战.
神经成像技术的进步对于了解认知过程中的大脑功能至关重要.

研究的目的:

开发一种混合深度学习框架,从EEG数据中捕获时空特征.
通过使用EEG信号来提高想象中的英语单词的分类准确性.
通过将数据转化为连续的地形脑图来解决EEG空间分辨率的局限性.

主要方法:

脑电图数据转化为连续的地形脑图,以表示时空信息.
混合深度学习模型的应用,特别是3D卷积神经网络 (3DCNNs) 和循环神经网络 (RNNs) 的顺序组合.
根据提取的时空特征对想象中的英语单词进行分类.

主要成果:

拟议的混合深度学习模型有效地从EEG地形图像中捕获了时空特征.
该方法在识别想象中的英语演讲方面取得了显著的平均准确率77.8%.
证明了整合EEG空间和时间数据用于认知状态识别的潜力.

关键词:

这是一个EEGEEGEEGEEGEEGEEGEEG.大脑地图 - - 大脑地图.想象中的话语想象中的话语神经成像是一种神经成像.地形图像图像地形图像图像

更多相关视频

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

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

相关实验视频

Last Updated: Jun 6, 2025

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

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

结论:

混合3DCNN-RNN框架为基于EEG的精神活动识别提供了一个有希望的解决方案.
将EEG数据转换为地形地图可以提高深度学习模型对大脑活动的表示.
这种方法通过提高想象语音检测的准确性来推进脑计算机接口领域的发展.