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

Reduced-intensity conditioning therapy with fludarabine, idarubicin, busulfan and cytarabine for allogeneic hematopoietic stem cell transplantation in acute myeloid leukemia and myelodysplastic syndrome.

Leukemia research·2013
Same author

Effects of 3, 5, 3'-triiodothyronine (t3) and follicle stimulating hormone on apoptosis and proliferation of rat ovarian granulosa cells.

The Chinese journal of physiology·2013
Same author

Cardiogenic shock from acute ST-segment elevation myocardial infarction induced by severe multivessel coronary vasospasm.

European heart journal·2013
Same author

[Comparative study on effects of electroacupuncture stimulation of Shenmen (HT 7) and Taiyuan (LU 9) on P 300 of event-related potentials and brain electrical activity mapping in healthy young adults].

Zhen ci yan jiu = Acupuncture research·2013
Same author

MiR-215 modulates gastric cancer cell proliferation by targeting RB1.

Cancer letters·2013
Same author

Low glucose utilization and neurodegenerative changes caused by sodium fluoride exposure in rat's developmental brain.

Neuromolecular medicine·2013

相关实验视频

Updated: May 16, 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

309

基于sEMG的手势识别,使用集成残余模块的多流自适应CNN.

Yutong Xia1, Dawei Qiu1, Cheng Zhang1

  • 1Shandong University of Traditional Chinese Medicine, Jinan, Shandong, China.

Frontiers in bioengineering and biotechnology
|May 14, 2025
PubMed
概括

这项研究引入了一种具有残余模块 (MSACNN-RM) 的新型多流自适应卷积神经网络,用于改进表面电肌图的手势识别. MSACNN-RM模型显著增强了特征提取,从而提高了识别复杂和稀疏手势的准确性.

科学领域:

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

背景情况:

  • 表面电肌图 (sEMG) 对于手势识别至关重要,但当前的深度学习模型在有效的特征提取方面扎,特别是在稀疏信号和多姿势场景中.
  • 现有的卷积神经网络 (CNN) 在sEMG数据中捕获复杂模式时经常表现出局限性,影响了整体识别性能.

研究的目的:

  • 开发一个先进的深度学习模型,用于增强sEMG手势识别.
  • 为了克服不足的特征提取和在识别sEMG信号中的稀疏和多姿势时的低准确性所带来的挑战.

主要方法:

  • 提出了一个多流自适应卷积神经网络与残余模块 (MSACNN-RM).
  • 集成了多个CNN流,自适应卷积层和剩余模块,以提高功能提取和学习能力.
  • 利用多流卷积和自适应模块与ResNet块相结合,从稀疏的sEMG信号中提取关键的手势特征.

主要成果:

  • 实现了高识别准确度:98.24%在Ninapro DB1上,93.52%在Ninapro DB2上,92.27%在Ninapro DB4上.
  • 与现有的深度学习模型相比,在sEMG手势识别方面表现出卓越的性能.
  • 有效地提高了模型从sEMG信号中提取和理解复杂数据模式的能力.
关键词:
适应性的卷积神经网络这是手势识别,是手势识别.多流卷积神经网络是多流卷积神经网络.剩余的模块 剩余的模块sEMG 的意思是说.

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

2.5K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

331

相关实验视频

Last Updated: May 16, 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

309
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

2.5K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

331

结论:

  • MSACNN-RM模型显示出对准确和强大的sEMG手势识别的重大承诺.
  • 未来的工作重点应该是开发通用算法,以解决sEMG信号的个体间变异,并优化网络以减少计算负载.