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

Anthropomorphic Robotic Hand Prosthesis Developed for Children.

Biomimetics (Basel, Switzerland)·2024
Same author

A Novel Active Device for Shoulder Rotation Based on Force Control.

Sensors (Basel, Switzerland)·2023
Same author

(MARGOT) Monocular Camera-Based Robot Grasping Strategy for Metallic Objects.

Sensors (Basel, Switzerland)·2023
Same author

Robust Fastener Detection Based on Force and Vision Algorithms in Robotic (Un)Screwing Applications.

Sensors (Basel, Switzerland)·2023
Same author

Validation of a Hybrid Exoskeleton for Upper Limb Rehabilitation. A Preliminary Study.

Sensors (Basel, Switzerland)·2021
Same author

Efficient Upper Limb Position Estimation Based on Angular Displacement Sensors for Wearable Devices.

Sensors (Basel, Switzerland)·2020

相关实验视频

Updated: Jun 23, 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

434

双流长短时间内存特征融合分类器用于表面肌电图手势识别.

Kexin Zhang1, Francisco J Badesa1, Yinlong Liu2

  • 1Centre for Automation and Robotics (CAR) UPM-CSIC, Universidad Politécnica de Madrid (UPM), 28006 Madrid, Spain.

Sensors (Basel, Switzerland)
|June 19, 2024
PubMed
概括
此摘要是机器生成的。

一个新的轻量级模型通过融合信号特征来改善假肢的电肌图学 (EMG) 手势识别. 这种双流LSTM分类器为实时控制提供了高准确度,并降低了计算成本.

关键词:
深度学习是一种深度学习.双流LSTM是双流的LSTM.功能融合 功能融合 功能融合这是手势识别,是手势识别.

更多相关视频

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

2.7K
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

498

相关实验视频

Last Updated: Jun 23, 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

434
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

2.7K
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

498

科学领域:

  • 生物医学工程 生物医学工程
  • 人与计算机的交互
  • 机器学习 机器学习

背景情况:

  • 电肌图 (EMG) 信号识别对于智能假肢和人机交互至关重要.
  • 当前的机器学习和深度学习方法面临诸如手动特征提取,过拟合和适应能力低等挑战.
  • 现有的深度学习模型经常使用复杂的架构,导致计算低效率和潜在的准确性限制.

研究的目的:

  • 开发一种新的,轻量级的模型,以改进基于EMG的手势识别.
  • 与现有方法相比,提高分类准确性和降低计算成本.
  • 通过手势识别,实现对智能假肢的更有效和高效的控制.

主要方法:

  • 提出了一种双流LSTM特征融合分类器,集成五个时间域EMG特征和原始数据.
  • 采用一维卷积神经网络 (CNN) 和长短期记忆 (LSTM) 层进行特征处理和分类.
  • 利用简单而有效的架构来捕获全球EMG信号特征,减少计算需求.

主要成果:

  • 在公共DB1数据集 (52个手势,27个受试者) 上获得了89.66%的准确性.
  • 演示了每种手势的快速推断时间为87.6毫秒,适合实时应用.
  • 在DB2数据集上验证,达到91.74%的学科平均准确率.

结论:

  • 拟议的双流LSTM模型有效地融合了时间域特征和原始EMG数据,以提升信息提取.
  • 轻量级架构为EMG手势识别提供了高效和适应性的解决方案.
  • 该模型的性能可与复杂的深度学习网络相提并论,为实时假肢控制提供了实用的方法.