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

Montelukast alleviates levels of inflammatory factors and chemokines in patients with allergic rhinitis.

Inflammopharmacology·2026
Same author

Digital image processing realized by memristor-based technologies.

Discover nano·2023
Same author

EGR1 Promotes Ovarian Hyperstimulation Syndrome Through Upregulation of SOX9 Expression.

Cell transplantation·2023
Same author

The application of HER2 and CD47 CAR-macrophage in ovarian cancer.

Journal of translational medicine·2023
Same author

Identification of copy number variation in Tibetan sheep using whole genome resequencing reveals evidence of genomic selection.

BMC genomics·2023
Same author

Association of living arrangements with all-cause mortality among older adults: a propensity score-matched cohort study.

BMC public health·2023

相关实验视频

Updated: Jul 29, 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

670

基于MEMS设备的手势识别通过可穿戴计算.

Huihui Wang1, Bo Ru2, Xin Miao2

  • 1School of Intelligence and Electronic Engineering, Dalian Neusoft University of Information, Dalian 116023, China.

Micromachines
|May 27, 2023
PubMed
概括
此摘要是机器生成的。

这项研究探讨了基于惯性传感器的手势识别,发现随机森林算法最适合静态手势. 一个注意力机制显著提高了动态手势识别准确度,达到98.3%.

关键词:
深度学习是一种深度学习.这是手势识别,是手势识别.隐藏的马尔科夫模型惯性传感器是一种无动态传感器.支持矢量机器的支持矢量机器.

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

3.9K
Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification
07:47

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Published on: February 14, 2018

11.3K

相关实验视频

Last Updated: Jul 29, 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

670
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

3.9K
Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification
07:47

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Published on: February 14, 2018

11.3K

科学领域:

  • 人与计算机的交互
  • 可穿戴技术可穿戴技术
  • 机器学习 机器学习

背景情况:

  • 手势识别对于VR,医学诊断和机器人技术至关重要.
  • 目前的方法包括基于惯性传感器和基于摄像头视觉的方法.
  • 光学方法面临着像反射和遮蔽这样的局限性.

研究的目的:

  • 使用微型惯性传感器研究静态和动态手势识别.
  • 评估用于静态手势识别的机器学习算法.
  • 评估隐藏的马尔科夫模型和基于注意力的LSTM,以实现动态手势识别.

主要方法:

  • 通过数据手套收集的手势数据,通过Butterworth低通过和规范化进行预处理.
  • 使用圆形配件和辅助细分进行磁力计校正,用于数据处理.
  • 静态手势识别采用支持向量机 (SVM),反向传播神经网络 (BP),决策树 (DT) 和随机森林 (RF).
  • 动态手势识别利用隐藏马尔科夫模型 (HMM) 和双向长期和短期记忆神经网络模型 (Attention-BiLSTM) 的注意偏差机制,与传统的LSTM相比.

主要成果:

  • 随机森林实现了对静态手势的最高准确度和最快的识别时间.
  • 注意力机制显著提高了动态手势的LSTM模型准确性,在六轴数据集中达到98.3%.
  • 分析显示了基于特征数据集的复杂动态手势的准确性差异.

结论:

  • 微型惯性传感器为手势识别提供了可行的替代方案,克服了光学限制.
  • 随机森林对于静态手势识别任务非常有效.
  • 注意力机制大大提高了深度学习模型在动态手势识别中的性能.