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

Author Correction: Regulatory T cells in the mouse hypothalamus control immune activation and ameliorate metabolic impairments in high-calorie environments.

Nature communications·2026
Same author

Lysosomal exocytosis by macrophages as a druggable mechanism for anti-inflammatory clearance of dead adipocytes in adipose tissue.

Cell death & disease·2025
Same author

Hand Gesture Recognition on Edge Devices: Sensor Technologies, Algorithms, and Processing Hardware.

Sensors (Basel, Switzerland)·2025
Same author

The Effect of Polyethylene Terephthalate Nanoplastics on Amyloid-β Peptide Fibrillation.

Molecules (Basel, Switzerland)·2025
Same author

Analysis of Polymer/siRNA Nanoparticle Efficacy and Biocompatibility in 3D Air-Liquid Interface Culture Compared to 2D Cell Culture.

Pharmaceutics·2025
Same author

Regulatory T cells in the mouse hypothalamus control immune activation and ameliorate metabolic impairments in high-calorie environments.

Nature communications·2025

相关实验视频

Updated: Jun 26, 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

455

端到端的超声波手势识别系统

Elfi Fertl1,2, Do Dinh Tan Nguyen1, Martin Krueger1

  • 1Infineon Technologies AG, 85579 Neubiberg, Germany.

Sensors (Basel, Switzerland)
|May 11, 2024
PubMed
概括

这项研究引入了一种新的机器学习方法,用于使用低成本传感器进行基于超声波的手势识别 (HGR). 该方法通过直接处理原始回声数据来实现高精度,简化了有效的人与计算机交互的过程.

关键词:
富里叶变换是什么意思 富里叶变换这是一个HMI.MEMS 超声波传感器的超声波传感器机器学习是机器学习.预处理 预处理

更多相关视频

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

707
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 26, 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

455
Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

707
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:

  • 人与计算机的交互
  • 信号处理 信号处理
  • 机器学习 机器学习

背景情况:

  • 在电子设备中对直观输入方法的需求日益增加.
  • 目前基于超声波的手势识别 (HGR) 系统的稳定性和准确性的局限性.
  • 需要具有成本效益和功率效率的HGR解决方案.

研究的目的:

  • 为HGR提供一种基于机器学习 (ML) 的全新端到端解决方案.
  • 为了利用低成本的微电机械 (MEMS) 系统超声波传感器.
  • 为了证明高精度与最小的数据预处理.

主要方法:

  • 开发一个定制的硬件设置,配有四个MEMS超声波传感器在不同的安排.
  • 通过ML模型直接处理原始超声波回声样本.
  • 对各种ML模型的基准测试,包括CNN,GRU,LSTM,ViT和CrossViT.

主要成果:

  • 通过LSTM,ViT和CrossViT模型实现了超过88%的准确性.
  • 证明了最小的预处理,即使省略了富里埃变换,也会产生高精度.
  • 通过ML模型展示了直接原始回声样本处理的有效性.

结论:

  • 对于高精度超声波HGR使用具有成本效益的MEMS传感器,最小的预处理就足够了.
  • 通过紧的ML模型进行直接信号处理,可以实现低成本,高功率的HGR.
  • 这种方法为使用视觉,WiFi或雷达的现有HGR系统提供了可行的替代方案.