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

A review on the production of P-enriched hydro/bio-char from solid waste: Transformation of P and applications of hydro/bio-char.

Chemosphere·2022
Same author

Longitudinal Changes in Peripapillary Retinal Nerve Fiber Layer and Macular Ganglion Cell Inner Plexiform Layer in Progressive Myopia and Glaucoma Among Adolescents.

Frontiers in medicine·2022
Same author

Preparation of flexible and UV-blocking films from lignin-containing cellulose incorporated with tea polyphenol/citric acid.

International journal of biological macromolecules·2022
Same author

Association of Mannose-Binding Lectin 2 Gene Polymorphism with Tuberculosis Based on <i>Mycobacterium tuberculosis</i> Lineages.

Infection and drug resistance·2022
Same author

Characteristic Assessment of Angiographies at Different Depths with AS-OCTA: Implication for Functions of Post-Trabeculectomy Filtering Bleb.

Journal of clinical medicine·2022
Same author

In<sub>2</sub>S<sub>3</sub> nanoflakes grounded in Bi<sub>2</sub>WO<sub>6</sub> nanoplates: A novel hierarchical heterojunction catalyst anchored on W mesh for efficient elimination of toluene.

Environmental research·2022

相关实验视频

Updated: Sep 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

751

基于应变传感器的多尺度注意力融合手势识别算法

Zhiqiang Zhang1, Jun Cai1, Xueyu Dai1

  • 1School of Electrical and Information Engineering, Anhui University of Science and Technology, Huainan 232001, China.

Sensors (Basel, Switzerland)
|July 12, 2025
PubMed
概括

这项研究介绍了MACLiteNet,这是一个轻量级的网络,用于使用张力计信号进行手势识别. 它实现了高精度和效率,在复杂的场景中优于传统的表面电肌图 (sEMG) 方法.

科学领域:

  • 生物医学工程 生物医学工程
  • 人与计算机的交互
  • 信号处理 信号处理

背景情况:

  • 表面电肌图 (sEMG) 广泛用于手势识别,但受到个体变化和传感器放置问题的困扰.
  • 张力计信号为捕捉关节变形提供了更大的环境适应性.
  • 现有的方法在应变信号的多通道,时间和振幅变化的性质上扎.

研究的目的:

  • 开发一种强大而高效的方法,用于使用张力计信号进行动态手势识别.
  • 在不受限制的环境中解决sEMG的局限性.
  • 为改进应变信号分析提出一个轻量化混合注意力网络.

主要方法:

  • 提出了MACLiteNet,一个轻量级的混合注意力网络.
  • 集成的局部时间建模,多尺度融合和通道重建.
  • 根据自行收集的张力计数据集和NinaPro DB1 (sEMG) 基准进行评估.

主要成果:

  • 在压力计数据集上,MACLiteNet的准确度达到99.71%,在NinaPro DB1数据集上达到98.45%.
  • 该网络的参数仅为0.22M,计算成本为0.10 GFLOPs.
  • 在准确性,效率和跨模式泛化方面表现出卓越的性能.
关键词:
跨模式识别的跨模式识别.动态手势识别功能 动态手势识别混合注意力机制 混合注意力机制多尺度特征融合的多尺度特征融合应变传感器 应变传感器

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

4.1K
Strain Sensing Based on Multiscale Composite Materials Reinforced with Graphene Nanoplatelets
09:38

Strain Sensing Based on Multiscale Composite Materials Reinforced with Graphene Nanoplatelets

Published on: November 7, 2016

8.9K

相关实验视频

Last Updated: Sep 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

751
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

4.1K
Strain Sensing Based on Multiscale Composite Materials Reinforced with Graphene Nanoplatelets
09:38

Strain Sensing Based on Multiscale Composite Materials Reinforced with Graphene Nanoplatelets

Published on: November 7, 2016

8.9K

结论:

  • MACLiteNet为可靠和高效的压力驱动交互系统提供了一个有前途的解决方案.
  • 提出的方法克服了sEMG在动态手势识别方面的局限性.
  • 突出了压力计信号在人机交互中的潜力.