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

Improving Sleep Quality and Quantity in Hospitalized Patients With Melatonin: A Quality Improvement Project at HCA (Hospital Corporation of America) Oak Hill Hospital.

Cureus·2026

Same author

Recurrent, Acute Limb Ischemia Secondary to Arterial Thrombosis: A Devastating Complication in the Setting of Severe COVID-19 Infection.

HCA healthcare journal of medicine·2025

Same author

Centroparietal Alpha/Beta Asymmetry in Response to Urgency Elicited by Upper Body Vibration.

IEEE transactions on haptics·2025

Same author

Analyzing handwriting legibility through hand kinematics.

Frontiers in artificial intelligence·2025

Same author

BandFocusNet: A Lightweight Model for Motor Imagery Classification of a Supernumerary Thumb in Virtual Reality.

IEEE open journal of engineering in medicine and biology·2025

Same author

Neuro-motor controlled wearable augmentations: current research and emerging trends.

Frontiers in neurorobotics·2024

Search research articles

相关实验视频

Updated: Feb 17, 2026

Using Facial Electromyography to Assess Facial Muscle Reactions to Experienced and Observed Affective Touch in Humans

Using Facial Electromyography to Assess Facial Muscle Reactions to Experienced and Observed Affective Touch in Humans

Published on: March 15, 2019

在多种模式中使用EEG和深度学习来评估触觉体验:将刺激与自我报告联系起来.

Haneen Alsuradi¹, Yonas Atinafu², Mohamad Eid¹

¹Engineering Division, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates.

Frontiers in neuroscience

|February 16, 2026

概括

这项研究表明,使用物理刺激 (PS) 参数来训练脑计算机接口 (BCI) 进行触觉反,比使用自我报告 (SR) 感知更有效. 经过PS训练的模型为自适应触觉接口提供了稳定和更高的性能.

关键词:

这是一个EEGEEGEEGEEGEEGEEGEEG.认知界面 - 认知界面深度学习 (deep learning) 是一种深度学习.触觉学是一种触觉学.自我报告自我报告

更多相关视频

Assessing the Multiple Dimensions of Engagement to Characterize Learning: A Neurophysiological Perspective

Assessing the Multiple Dimensions of Engagement to Characterize Learning: A Neurophysiological Perspective

Published on: July 1, 2015

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

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

Published on: July 26, 2013

相关实验视频

Last Updated: Feb 17, 2026

Using Facial Electromyography to Assess Facial Muscle Reactions to Experienced and Observed Affective Touch in Humans

Using Facial Electromyography to Assess Facial Muscle Reactions to Experienced and Observed Affective Touch in Humans

Published on: March 15, 2019

Assessing the Multiple Dimensions of Engagement to Characterize Learning: A Neurophysiological Perspective

Assessing the Multiple Dimensions of Engagement to Characterize Learning: A Neurophysiological Perspective

Published on: July 1, 2015

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

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

Published on: July 26, 2013

科学领域:

神经科学是一个神经科学.
人与计算机的交互
机器学习机器学习

背景情况:

传统的触觉界面评估使用主观自我报告,限制客观性和实时适应性.
认知触觉接口利用神经生理学措施,如脑电图 (EEG) 和深度学习进行客观评估.
一个关键的挑战在于标记神经反应:使用物理刺激 (PS) 参数或自我报告 (SR) 感知.

研究的目的:

系统地调查基于PS和SR的标签对基于EEG的触觉反深度学习模型性能的影响.
通过四种触觉反方式,比较PS和SR标签方案的有效性.
确定标签如何影响模型稳定性和对触觉刺激的神经反应解码的准确性.

主要方法:

训练有素的深度学习模型 (ATCNet,EEG Inception,EEG Conformer) 使用由PS参数和SR感知标记的EEG数据.
评估了四种触觉模式的模型性能:延迟力反 (DFF),指尖振动反 (FVF),上肢振动反 (UVF) 和指尖热反 (FTF).
采用集团级别的离开一个主体 (LOSO) 交叉验证策略来评估模型的通用性.

主要成果:

与SR标记型模型相比,在所有测试模式中,使用PS标签训练的模型始终表现出更稳定和更高的性能.
标记PS的模型的性能增长在接近感知值的刺激水平时最明显,其中SR标签表现出更大的个体间变化.
基于EEG的模型比主观报告更接近物理刺激参数,特别是在模两可的感知条件下.

结论:

与自我报告 (SR) 标签相比,物理刺激 (PS) 标签为训练认知触觉接口中的深度学习模型提供了更强大,更客观的方法.
经过PS训练的解码器作为触觉反系统的有效基础表示,可适应用户特定的SR数据.
这项研究支持使用基于PS的模型来开发更可靠和更适应的触觉接口,特别是在具有挑战性的感知模式中.