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

An Unsupervised Image Enhancement Framework for Multiple Fault Detection of Insulators.

Sensors (Basel, Switzerland)·2025
Same author

Power Line Segmentation Algorithm Based on Lightweight Network and Residue-like Cross-Layer Feature Fusion.

Sensors (Basel, Switzerland)·2025
Same author

Association between genetic polymorphisms and gestational diabetes mellitus susceptibility in a Chinese population.

Frontiers in endocrinology·2024
Same author

T2 mapping for quantitative assessment of ankle cartilage of weightlifters.

Scientific reports·2023
Same author

Association of miR-196a2 and miR-27a polymorphisms with gestational diabetes mellitus susceptibility in a Chinese population.

Frontiers in endocrinology·2023
Same author

A Lightweight Algorithm for Insulator Target Detection and Defect Identification.

Sensors (Basel, Switzerland)·2023

相关实验视频

Updated: Jan 17, 2026

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

1.2K

基于sEMG的手势识别使用Sigimg-GADF-MTF和多流卷积神经网络.

Ming Zhang1,2, Leyi Qu1,2, Weibiao Wu1,2

  • 1School of Electronic & Electrical Engineering, Wuhan Textile University, Wuhan 430200, China.

Sensors (Basel, Switzerland)
|September 19, 2025
PubMed
概括

本研究引入了一种基于表面电肌图 (sEMG) 的手势识别的新算法,通过将sEMG信号处理成图像并使用多流卷积神经网络来实现高精度.

关键词:
格拉米的角度差异场 (GADF)马尔科夫过渡场 (MTF) 是一个马尔科夫过渡场.这是手势识别,是手势识别.多流卷积神经网络 (MSCNN) 是一个多流卷积神经网络.这是一个 sEMG 信号.

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

5.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

相关实验视频

Last Updated: Jan 17, 2026

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

1.2K
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

5.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

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:

  • 表面电肌图 (sEMG) 信号包含丰富的时间,静态和动态信息,这些信息对于手势识别至关重要.
  • 现有的方法往往难以充分利用这些复杂的信号特征,限制识别精度.
  • 由于sEMG的时间特征,对动作幅度和肌肉招募敏感,因此需要先进的处理技术.

研究的目的:

  • 开发一种基于sEMG的创新手势识别算法,全面利用时间,静态和动态信号特征.
  • 引入新的数据处理方法 (Sigimg,格拉姆角差异场 (GADF),马尔科夫过渡场 (MTF)) 用于sEMG信号转换.
  • 将这些方法与多流卷积神经网络 (MSCNN) 和多流融合策略相结合,以提高识别能力.

主要方法:

  • 使用滑动窗口将多通道sEMG信号重新排列成一个2D图像 (Sigimg).
  • 通过GADF和MTF方法将单个sEMG通道转换为2D子图像.
  • 横向拼接GADF和MTF子图像,用Sigimg,GADF和MTF图像构建一个训练数据集,并应用具有完全连接层融合的MSCNN.

主要成果:

  • 拟议的Sigimg-GADF-MTF-MSCNN算法在Ninapro DB1数据集上实现了88.4%的平均准确性.
  • 这种准确性超过了大多数主流的手势识别模型.
  • 在自主开发的sEMG采集平台上进行概括测试,平均准确率为82.4%,验证了算法的有效性.

结论:

  • Sigimg-GADF-MTF-MSCNN算法有效地利用多通道sEMG信号特征来实现准确的手势识别.
  • 与现有方法相比,新型数据处理和多流融合策略显著提高了性能.
  • 该算法展示了强大的概括能力,显示了对现实世界应用的承诺.