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

Three-Dimensional Force System01:30

Three-Dimensional Force System

2.0K
In mechanical engineering, a three-dimensional force system is a system of forces acting in three dimensions, with forces applied along the x, y, and z coordinate axes. The three-dimensional force system is an important concept in mechanical engineering, as it allows engineers to understand and analyze the behavior of objects and structures in three dimensions. By understanding the forces acting on a system, engineers can design more efficient and effective mechanical systems that can withstand...
2.0K

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

Dynamic task-related prefrontal functional networks evolved in Stroop Color-Word tasks measured by fNIRS.

Cognitive neurodynamics·2026
Same author

Extracellular matrix stiffness orchestrates NETs formation and mTOR-Driven metabolic reprogramming in lung cancer.

Cancer letters·2026
Same author

Evaluating Stroke-Related Motor Impairment and Recovery Using Macroscopic and Microscopic Features of HD-sEMG.

Bioengineering (Basel, Switzerland)·2025
Same author

Wearable technologies for assisted mobility in the real world.

Nature communications·2025
Same author

A Real-Time High-Density sEMG Gesture Recognition System Distilled from a Deep Model.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

DGPC-Net: Dual Branch Gaussian Process Constrained Network for Spinal Cord Stimulation Effect Prediction.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025

相关实验视频

Updated: Jun 6, 2025

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

401

使用深度神经网络和交叉关节转移学习改进了基于表面电肌图的手腕力估计.

Haopeng Wang1, He Wang1, Chenyun Dai2

  • 1Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA 01609, USA.

Sensors (Basel, Switzerland)
|November 27, 2024
PubMed
概括
此摘要是机器生成的。

使用深度神经网络 (DNN) 的转移学习 (TL) 改进了基于表面电肌图 (sEMG) 的对上肢关节的力估计. 交叉关联的TL提高了准确性和减少了数据需求,为未来研究中更大,更多样化的数据集铺平了道路.

关键词:
在美国,CNN是CNN.这是LSTM的LSTM.深度神经网络是一个神经网络.一个电心图 (electromyogram) 是一个电心图.估计力量的估计力.转移学习转移学习

更多相关视频

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.5K
Author Spotlight: Enhancing Grasping Abilities for Hemiplegic Patients with Flexible Robotic Limbs
03:55

Author Spotlight: Enhancing Grasping Abilities for Hemiplegic Patients with Flexible Robotic Limbs

Published on: October 27, 2023

2.0K

相关实验视频

Last Updated: Jun 6, 2025

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

401
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.5K
Author Spotlight: Enhancing Grasping Abilities for Hemiplegic Patients with Flexible Robotic Limbs
03:55

Author Spotlight: Enhancing Grasping Abilities for Hemiplegic Patients with Flexible Robotic Limbs

Published on: October 27, 2023

2.0K

科学领域:

  • 生物医学工程 生物医学工程
  • 机器学习 机器学习
  • 康复技术 康复技术 康复技术

背景情况:

  • 表面电肌图 (sEMG) 信号对于非侵入性人类运动分析至关重要.
  • 深度神经网络 (DNN) 和转移学习 (TL) 显示出改善基于sEMG的力估计的前景.
  • 现有的TL研究受限于关注单个联合申请,限制了数据集的大小和多样性.

研究的目的:

  • 调查交叉关节TL的有效性,用于基于sEMG的两个上肢关节之间的力估计.
  • 评估四种不同的DNN架构,用于这个跨关节TL应用程序.
  • 为了确定捕获sEMG力依赖性的最佳滑动窗特征.

主要方法:

  • 采用了四个DNN架构 (两个前,两个反复),用于基于sEMG的力估计.
  • 转移学习是通过对肘部关节数据的预训练模型和对手腕数据的微调实现的.
  • 在DNN模型中使用了特征工程和特征学习方法.

主要成果:

  • 发现sEMG力依赖是短期的 (<400 ms),表明滑动窗口足够.
  • DNN 减少了必要的滑动窗口长度,以准确估计力.
  • 使用TL的卷积神经网络 (CNN) 仅使用20秒的训练数据实现了6.03 ± 0.49%的最大自愿扭矩误差,优于其他模型.

结论:

  • 交叉关节TL是一种可行的策略,可以提高基于sEMG的力量估计准确度,并减少训练数据要求.
  • 这些发现表明,复杂的重复结构可能不必要,并且滑窗DNN是有效的.
  • 成功的交叉联合TL可以显著丰富未来的生物力学和康复的深度学习研究的数据多样性.