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

Safety-aware transformer-enhanced unified multi-task perception for road anomaly detection, drivable area segmentation and lane estimation.

Scientific reports·2026

Same author

Hybrid CNN-GCN network with dynamic gating and scale-aware preprocessing for pedestrian crossing intention prediction in Indian road conditions.

Scientific reports·2026

Same author

Deep learning-based eye sign communication system for people with speech impairments.

Disability and rehabilitation. Assistive technology·2025

Same author

Coconut tree modeling based on abiotic factors and modified cosserat rod theory.

Plant methods·2025

Same author

Design, analysis and performance evaluation of a hand gesture platform for navigation.

Technology and health care : official journal of the European Society for Engineering and Medicine·2019

Search research articles

相关实验视频

Updated: Jun 4, 2025

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

一个基于实证模型的算法,用于移除运动图像中的运动引起的人工物,使用优化的CNN模型对EEG数据进行分类.

Rajesh Kannan Megalingam¹, Kariparambil Sudheesh Sankardas¹, Sakthiprasad Kuttankulangara Manoharan¹

¹Humanitarian Technology (HuT) Labs, Department of Electronics and Communication Engineering, Amrita Vishwa Vidyapeetham, Amritapuri 690525, India.

Sensors (Basel, Switzerland)

|December 17, 2024

概括

这项研究引入了一种新的方法,可以从脑电图 (EEG) 数据中删除脑电脑接口 (BCI) 的运动器件. 新方法在分类运动图像 (MI) 脑电图信号方面实现了94.04%的准确性,帮助轮椅使用者.

关键词:

大脑计算机接口 (BCI)卷积神经网络 (CNN) 是一种神经网络.经验错误模型的实证错误模型.运动文物运动文物运动成像 - 电脑图像学 (MI-EEG)四肢的人.轮椅是一个轮椅.

更多相关视频

Reliable Acquisition of Electroencephalography Data during Simultaneous Electroencephalography and Functional MRI

Reliable Acquisition of Electroencephalography Data during Simultaneous Electroencephalography and Functional MRI

Published on: March 19, 2021

Best Current Practice for Obtaining High Quality EEG Data During Simultaneous fMRI

Best Current Practice for Obtaining High Quality EEG Data During Simultaneous fMRI

Published on: June 3, 2013

相关实验视频

Last Updated: Jun 4, 2025

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

Reliable Acquisition of Electroencephalography Data during Simultaneous Electroencephalography and Functional MRI

Reliable Acquisition of Electroencephalography Data during Simultaneous Electroencephalography and Functional MRI

Published on: March 19, 2021

Best Current Practice for Obtaining High Quality EEG Data During Simultaneous fMRI

Best Current Practice for Obtaining High Quality EEG Data During Simultaneous fMRI

Published on: June 3, 2013

科学领域:

生物医学工程生物医学工程
神经科学是一个神经科学.
信号处理信号处理

背景情况:

脑电图 (EEG) 是用于脑电脑接口 (BCI) 系统的有价值的非侵入性工具,特别适用于严重移动障碍的人.
机动图像EEG (MI-EEG) 数据分类对于BCI应用至关重要,它可以控制轮椅等设备.
运动工件显著降低了EEG信号质量,这对移动个人 (如轮椅使用者) 使用的BCI系统构成了挑战.

研究的目的:

开发和验证基于实证错误模型的工件删除方法,用于MI-EEG数据的跨主题分类.
为了提高MI-EEG分类的准确性,用于实际的BCI应用,特别是轮椅使用者.
通过解决运动诱导的工件来提高运动图像BCI的解码效率.

主要方法:

提出了一个经验错误模型,包含惯性传感器数据,轮椅,受试者体重和地形摩擦.
开发了一种基于卷积神经网络 (CNN) 的深度学习算法,用于MI-EEG分类.
使用三个轮椅在五个不同的地形 (道路,,混凝土,地毯,大理石) 上记录了文物数据.

主要成果:

在四个运动图像类别 (左,右,前,后) 之间区分时,获得了94.04%的分类准确度.
证明了拟议的CNN和经验模型在移除运动文物方面的有效性.
与现有的最先进的技术相比,展示了优越的性能.

结论:

提出的基于经验错误模型的文物删除方法显著提高了MI-EEG分类的准确性.
这种方法提供了一种潜在的有效解决方案,以提高轮椅使用者的BCI解码效率.
这项研究促进了实际的BCI应用,使运动图像信号的可靠解释能够实现,尽管运动文物.