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

A plastoglobuli-localized enzyme links phenylalanine biosynthesis to translational homeostasis in maize.

Nature communications·2026

Same author

Effect of Mechanical Polishing on Rice Flavor: Comparison and Exploration of Key Aroma Characteristics Components.

Foods (Basel, Switzerland)·2026

Same author

Combined inhibition of BETs and HDACs as a potential epigenetics-based therapy for malignant rhabdoid tumor.

Cell death & disease·2026

Same author

Arginine metabolism and the NF-ĸB pathway jointly regulate the airway inflammation in asthma mediated by ILC2s.

International immunopharmacology·2026

Same author

Debranching and OSA esterification of waxy maize starch: effects on nanoparticle properties and emulsion performance.

Food chemistry: X·2026

Same author

Lactylation-driven PDLIM1/PDAP1 axis remodels the inflammatory landscape of acute lung injury: mechanistic insights and precision intervention.

Frontiers in immunology·2026

Search research articles

相关实验视频

Updated: Jul 17, 2025

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Published on: May 10, 2024

在线半监督学习用于运动图像EEG分类.

Li Zhang¹, Changsheng Li¹, Run Zhang²

¹State Key Laboratory of Power Transmission Equipment & System Security and New Technology, School of Electrical Engineering, Chongqing University, Chongqing, 400044, People's Republic of China.

Computers in biology and medicine

|September 7, 2023

概括

本研究介绍了一种高效的在线半监督学习方案,以提高脑计算机接口 (BCI) 性能,用于运动成像 (MI) 任务. 该方法通过使用未标记的数据来提高分类准确性,克服了传统BCI系统的局限性.

关键词:

大脑与计算机的接口.编辑了最近邻居规则.极端学习的机器学习.半监督学习半监督学习合成少数人过量抽样技术

更多相关视频

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients

Published on: September 1, 2023

Functional Near Infrared Spectroscopy of the Sensory and Motor Brain Regions with Simultaneous Kinematic and EMG Monitoring During Motor Tasks

Functional Near Infrared Spectroscopy of the Sensory and Motor Brain Regions with Simultaneous Kinematic and EMG Monitoring During Motor Tasks

Published on: December 5, 2014

相关实验视频

Last Updated: Jul 17, 2025

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Published on: May 10, 2024

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients

Published on: September 1, 2023

Functional Near Infrared Spectroscopy of the Sensory and Motor Brain Regions with Simultaneous Kinematic and EMG Monitoring During Motor Tasks

Functional Near Infrared Spectroscopy of the Sensory and Motor Brain Regions with Simultaneous Kinematic and EMG Monitoring During Motor Tasks

Published on: December 5, 2014

科学领域:

神经科学是一个神经科学.
机器学习机器学习
生物医学工程生物医学工程

背景情况:

大脑-计算机接口 (BCI) 中的数据标签耗时,并导致精神疲劳,阻碍了基于运动图像 (MI) 的BCI在现实世界中采用.
在线整合未标记的数据是改善BCI性能的一种较少探索的替代方案.

研究的目的:

开发和评估一个在线半监督学习计划,以提高基于MI的BCI的分类性能.
在BCI开发中应对数据稀缺和标签努力的挑战.

主要方法:

提出了一个在线半监督学习方案,使用规范加权在线顺序极端学习机器 (RWOS-ELM) 分类器.
实施了数据增强技术,结合合成少数群体过量采样和编辑最近邻居规则,用于初始和在线数据平衡.
循序渐进地更新分类器模型,使用平衡的,伪标记的数据块.

主要成果:

在两个公共MI数据集上的线下实验表明,拟议方案的性能优于现有方法.
与六名受试者进行的在线实验表明,通过从传入的未标记数据中学习,BCI性能逐渐得到改善.

结论:

拟议的在线半监督学习方案提供了高计算和内存效率.
这种方法对基于在线MI的BCI来说是有希望的,特别是当标记的培训数据有限时.