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

In Situ Water Quality Monitoring for the Assessment of Algae and Harmful Substances in Water Bodies with Consideration of Uncertainties.

Sensors (Basel, Switzerland)·2025
Same author

Magnetoelectric Energy Harvesting for Industrial IoT Applications: Frequency-Tunable Converter with Enhanced Performance.

Sensors (Basel, Switzerland)·2025
Same author

Kinetic Energy Harvesting with a Piezoelectric Patch Using a Bistable Laminate.

Micromachines·2025
Same author

Enhancing Localization Accuracy and Reducing Processing Time in Indoor Positioning Systems: A Comparative Analysis of AI Models.

Sensors (Basel, Switzerland)·2025
Same author

Electrochemical Switching of Laser-Induced Graphene/Polymer Composites for Tunable Electronics.

Polymers·2025
Same author

Rotating radial injection pattern for highly sensitive electrical impedance tomography of human lung anomalies.

Physiological measurement·2025

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

基于手势分类表现的sEMG特征评估方法的比较研究.

Hiba Hellara1,2, Rim Barioul1, Salwa Sahnoun2

  • 1Professorship for Measurements and Sensor Technology, Chemnitz University of Technology, Rechenhainer Straße 70, 09126 Chemnitz, Germany.

Sensors (Basel, Switzerland)
|June 19, 2024
PubMed
概括

选择正确的特征提取方法是使用电肌图 (EMG) 信号准确识别手势的关键. 递归特征消除 (RFE) 方法在提高准确性和减少特征数量方面显示出有希望.

关键词:
功能评估 功能评估 功能评估功能提取 特性提取功能选择 功能选择这是手势识别,是手势识别.肌肉图谱 肌肉图谱是指肌肉图谱,是指肌肉图谱.表面电力学图 (surface electromyography) 是一种表面电力学图.

更多相关视频

Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication
07:18

Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication

Published on: January 26, 2024

870
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

1.6K

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: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication
07:18

Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication

Published on: January 26, 2024

870
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

1.6K

科学领域:

  • 生物医学工程 生物医学工程
  • 机器学习 机器学习
  • 信号处理 信号处理

背景情况:

  • 精确的手势识别对于人机交互和假肢技术至关重要.
  • 电肌图 (EMG) 信号为捕捉手部运动提供了一种有希望的,非侵入性的方法.
  • 有效的特征提取和选择对于基于EMG的强大的手势分类至关重要.

研究的目的:

  • 系统地比较基于EMG的手势识别的六种过器和包装器特征评估方法.
  • 调查不同特征选择技术对分类准确性的影响.
  • 为了确定最佳的功能子集,以提高手势识别性能.

主要方法:

  • 从多个传感器的sEMG数据中提取了37个时间和频域特征.
  • 评估了六种特征选择方法,包括最小冗余最大相关性 (mRMR),递归特征消除 (RFE),相互信息 (MI) 和特征重要性 (FI).
  • 在基准和现实世界手势数据集上测试的方法,来自14名健康受试者执行15个练习.

主要成果:

  • RFE方法显示了提高分类准确性的潜力,选择了65个特征以达到97.14%的准确性.
  • 相互信息 (MI) 在200个特征中达到97.38%的准确性,而特征重要性 (FI) 在140个特征中达到97.62%.
  • 进一步的改进确定了三个额外的特征,将精度提高到97.38%,强调了特征选择对效率的重要性.

结论:

  • 选择特征选择方法显著影响基于EMG的手势识别精度.
  • 像RFE这样的方法可以减少特征维度,同时保持高分类性能.
  • 为了开发先进的手势识别系统,需要对功能选择优化进行进一步的研究.