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 Bi-Level Hybrid Framework for Multi-Target Path Planning of AGV Based on Particle Swarm Optimization and Bidirectional Rapidly Exploring Random Tree.

Sensors (Basel, Switzerland)·2026
Same author

Evaluation of cold resistance in pear (<i>Pyrus</i> L.) germplasms: integrating physiological and biochemical responses with anatomical traits under low temperature stress.

PeerJ·2026
Same author

Robust Rule-based Heuristic Assistance Strategy for a Semi-Active Shoulder Exoskeleton Used in Overhead Work.

IEEE transactions on bio-medical engineering·2026
Same author

Surface modification strategies of oral liposomes: functional design and barrier enhancement.

Frontiers in pharmacology·2026
Same author

A high-resolution electrostatically actuated MEMS Fabry-Pérot tunable filter for LWIR imaging and sensing applications.

Microsystems & nanoengineering·2026
Same author

Rheological Behavior and Aging Resistance of SBS/Lignin Composite Modified Asphalt.

Polymers·2026

相关实验视频

Updated: Jun 11, 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

一个新型的主动学习框架,用于通过表面电肌图识别跨主题的人类活动.

Zhen Ding1, Tao Hu2, Yanlong Li2

  • 1College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China.

Sensors (Basel, Switzerland)
|September 28, 2024
PubMed
概括

本研究介绍了使用可穿戴传感器进行人类活动识别 (HAR) 的积极学习框架. 该方法通过提高跨主题适应性和数据质量来改善外骨控制,优于现有技术.

关键词:
分类器的差异性不一致.这是一个跨主题的问题.人类活动的认可 人类活动的认可关系网络 关系网络.表面电动图信号的信号.可以穿戴的传感器.

更多相关视频

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

407
Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography
09:42

Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography

Published on: January 24, 2025

450

相关实验视频

Last Updated: Jun 11, 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
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

407
Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography
09:42

Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography

Published on: January 24, 2025

450

科学领域:

  • 生物医学工程 生物医学工程
  • 机器人技术 机器人技术 机器人技术
  • 机器学习 机器学习

背景情况:

  • 基于传感器的可穿戴式人类活动识别 (HAR) 对于先进的外骨控制至关重要.
  • 现有的HAR方法在数据质量和适应新用户 (跨主题适应) 上扎.

研究的目的:

  • 开发一个积极的学习框架,以在外骨架系统中提供强大的HAR.
  • 解决数据质量和穿戴式传感器数据跨主题适应方面的挑战.

主要方法:

  • 整合了一个关系网络架构与数据采样技术.
  • 使用辅助分类器来确定特定学科的边界.
  • 使用分类器差异用于数据显著性评估和分成样本/模板集.
  • 应用类别聚类用于参数调整和模板数据优化.

主要成果:

  • 拟议的框架在公开和自建数据集的所有统计指标上表现出卓越的表现.
  • 废弃实验证实了数据选在适应过程中的关键作用.
  • 在人类活动识别中实现了更高的准确性和通用性.

结论:

  • 积极学习框架有效地将HAR模型适应目标学科,提高准确性和通用性.
  • 该方法解决了基于可穿戴传感器的数据质量和跨主题适应的关键限制.
  • 这项工作验证了对外骨控制系统的用户独立HAR的实际实施.