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

Frequency-Dependent Bioimpedance Signatures of Ocular Tissues in Intact Ex Vivo Eyes Under Simulated Surgical Conditions.

bioRxiv : the preprint server for biology·2026
Same author

Effects of Aerobic Exercise on Heart Rate Variability and C-Reactive Protein in Middle-Aged Adults With Normal Weight and Overweight/Obesity: A Pilot Study.

Research in nursing & health·2026
Same author

Keypoint detection network for needle localization on intra-procedural MRI in MRI-guided liver interventions.

International journal of computer assisted radiology and surgery·2026
Same author

Control Modes of Teleoperated Surgical Robotic System's Tools in Ophthalmic Surgery.

IEEE transactions on medical robotics and bionics·2026
Same author

AI-Based Model Estimation for a Precision Positioning Stage Employing Multiple Control Switching.

Micromachines·2025
Same author

Integrated Control Strategies for a Precision Long-Travel Stage: Applications in Micro-Lens Fabrication.

Micromachines·2025

相关实验视频

Updated: Jul 12, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K

基于惯性测量单元和长短期记忆神经网络的人类姿势过渡时间检测.

Chun-Ting Kuo1, Jun-Ji Lin1, Kuo-Kuang Jen2

  • 1Department of Mechanical Engineering, National Taiwan University, Taipei 106319, Taiwan.

Biomimetics (Basel, Switzerland)
|October 27, 2023
PubMed
概括

这项研究使用了包括长期短期记忆 (LSTM) 在内的深度学习模型来检测人类姿势的变化和转变. 该LSTM模型展示了高精度和速度,为先进的人机交互应用铺平了道路.

关键词:
深度学习是一种深度学习.料前神经网络 (FNN) 是一个神经网络.人类活动识别 (HAR)人的姿势变化检测检测检测惯性测量单位 (IMU) 是指惯性测量单位.内部传感传感器 内部传感器长时间的短期记忆 (LSTM)

更多相关视频

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K
A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

10.5K

相关实验视频

Last Updated: Jul 12, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K
A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

10.5K

科学领域:

  • 机器人和人机交互的人机交互
  • 机器学习和深度学习
  • 生物医学工程和可穿戴技术

背景情况:

  • 人与机器人的互动正在工业和临床领域不断增长,增加了对精确人体姿势检测的需求.
  • 现有的研究主要集中在识别人类行为上,很大程度上忽视了姿势之间的关键过渡.
  • 检测姿势变化和转变对于无的人机协作和理解人类意图至关重要.

研究的目的:

  • 研究深度学习方法的有效性,特别是Feedforward神经网络 (FNN) 和长期短期记忆 (LSTM),用于检测人类姿势的变化.
  • 分析这些模型在识别不同人体运动 (站立,行走,坐着) 之间的过渡阶段的能力.
  • 评估采样率对LSTM网络检测姿势变化的性能的影响.

主要方法:

  • 两种深度学习模型FNN和LSTM被用来检测姿势变化.
  • 一个惯性测量单元 (IMU) 被戴在受试者的腿上,以收集用于训练和测试的联合参数数据.
  • 该研究引入了过渡阶段作为独特的特征,并检查了LSTM模型的各种采样率.

主要成果:

  • FNN和LSTM模型都实现了对人类姿势变化的高检测准确度.
  • 在速度和精度方面,LSTM模型显著超过了FNN,在100 Hz采样速率下达到95%的精度.
  • 经过训练的LSTM网络在检测不同受试者的姿势变化方面表现出有效性,这表明了一般化模型的潜力.

结论:

  • 深度学习模型,特别是LSTM,对于快速准确地检测人类姿势变化和转变非常有效.
  • 该研究成功地证明了在实时应用中使用IMU数据和深度学习来检测人类意图的可行性.
  • 这些发现为工程应用提供了基础性贡献,例如数字双胞胎,外骨和先进的人类意图控制系统.