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

Eye-Tracking Technologies for Cognitive Assessment After Acquired Brain Injury: Systematic Review.

JMIR rehabilitation and assistive technologies·2026
Same author

TrustInAging: Digital Tools for Healthy Aging.

Studies in health technology and informatics·2026
Same author

How improper dataset split hinders model generalizability: a systematic comparison in Human activity recognition and exercise evaluation tasks.

International journal of medical informatics·2026
Same author

Training Load Distribution Across Weekly Microcycles According to the Match Schedule During the Regular Season in a Professional Rink Hockey Team.

Journal of functional morphology and kinesiology·2026
Same author

Interplay between balance, gait kinematic and physical activity level in facioscapulohumeral muscular dystrophy.

Scientific reports·2025
Same author

Four-Week Exoskeleton Gait Training on Balance and Mobility in Minimally Impaired Individuals with Multiple Sclerosis: A Pilot Study.

Bioengineering (Basel, Switzerland)·2025

相关实验视频

Updated: Jan 16, 2026

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

44.0K

深度学习模型优化用于外骨架辅助行走期间从EMG数据中识别步行阶段.

Roberto Soldi1, Bruna Maria Vittoria Guerra1, Stefania Sozzi1

  • 1Laboratory of Bioengineering, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 Pavia, Italy.

Biomimetics (Basel, Switzerland)
|September 26, 2025
PubMed
概括
此摘要是机器生成的。

深度学习模型使用辅助外骨架的表面电肌学 (sEMG) 预测步行阶段. 优化的模型实现了95%的准确性,降低了参数和快速计算,以实现有效的康复.

关键词:
深度学习是一种深度学习.外骨架 (exoskeleton) 是一个外骨架.步态分析 步态分析超参数调整 超参数调整sEMG 的意思是

更多相关视频

Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis
11:16

Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis

Published on: July 22, 2014

16.7K
Methods to Quantify Pharmacologically Induced Alterations in Motor Function in Human Incomplete SCI
14:55

Methods to Quantify Pharmacologically Induced Alterations in Motor Function in Human Incomplete SCI

Published on: April 18, 2011

14.2K

相关实验视频

Last Updated: Jan 16, 2026

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

44.0K
Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis
11:16

Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis

Published on: July 22, 2014

16.7K
Methods to Quantify Pharmacologically Induced Alterations in Motor Function in Human Incomplete SCI
14:55

Methods to Quantify Pharmacologically Induced Alterations in Motor Function in Human Incomplete SCI

Published on: April 18, 2011

14.2K

科学领域:

  • 生物医学工程 生物医学工程
  • 康复技术 康复技术 康复技术
  • 医疗保健中的机器学习

背景情况:

  • 外骨架为运动功能障碍康复提供了有希望的解决方案.
  • 准确的在线控制辅助外骨架对于患者的步行辅助至关重要.
  • 表面电肌图 (sEMG) 信号反映了与运动相关的肌肉活动.

研究的目的:

  • 探索深度学习 (DL) 模型,在外骨架辅助行走期间使用sEMG数据进行在线步态阶段预测.
  • 优化DL模型以减少尺寸和计算成本,同时保持高精度.
  • 评估在线实施实时外骨控制的可行性.

主要方法:

  • 利用sEMG数据和关节动力学来预测步行阶段 (姿势/摇摆).
  • 采用跨学科设计进行模型概括.
  • 实现了超参数优化,以减少DL模型大小和计算需求.
  • 模拟了一个用例场景来评估在线实施的可行性.

主要成果:

  • 确定了一个DL模型,在步态阶段分类中达到约95%的准确性.
  • 显著减少了优化DL模型中的参数数量.
  • 在优化模型中实现了不到10ms的平均计算时间.
  • 引入了用于评估模型成本效益的权衡得分 (TOS) 度量.

结论:

  • 拟议的DL方法允许使用sEMG数据对下肢外骨进行准确的在线步行阶段预测.
  • 优化的DL模型为实时控制提供了可行的解决方案,增强了外骨架辅助康复.
  • 这些发现支持基于sEMG的DL模型在改善辅助外骨功能和患者结果方面的潜力.