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

Integrated multi-omics analyses reveal impaired energy homeostasis underlying tongue-rolling behavior in dairy cattle.

Veterinary journal (London, England : 1997)·2026
Same author

An AI-Based OCT System to Detect Diabetic Macular Edema: A Prospective Validation and Noninferiority Randomized Clinical Trial.

JAMA·2026
Same author

Chain entanglements enable regeneration of high-performance thermosets.

Nature materials·2026
Same author

Polyethylene terephthalate oligomers in indoor dust: Occurrence characteristics, exposure flux and health risk.

Environmental pollution (Barking, Essex : 1987)·2026
Same author

Engineered Probiotics Protect against <i>Pseudomonas aeruginosa</i> Post Antibiotic Exposure.

ACS synthetic biology·2026
Same author

A self-perpetuating cycle: how heavy metals shape DOM chemistry to promote their own immobilization in soil.

Environmental monitoring and assessment·2026

相关实验视频

Updated: Jul 12, 2025

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

3.8K

基于自我注意的深度卷积LSTM框架用于基于传感器的羽毛球活动识别

Jingyang Deng1, Shuyi Zhang1, Jinwen Ma1

  • 1School of Mathematical Sciences and LMAM, Peking University, Beijing 100871, China.

Sensors (Basel, Switzerland)
|October 28, 2023
PubMed
概括
此摘要是机器生成的。

这项研究引入了一个新的深度学习框架,用于基于传感器的羽毛球活动识别. 拟议的模型通过有效地从传感器数据中学习特征来实现高精度,优于现有方法.

关键词:
长时间短期记忆 (LSTM)羽毛球活动的认可.深度学习是一种深度学习.自己注意力自我注意力

更多相关视频

Biomechanical Analysis Methods to Assess Professional Badminton Players' Lunge Performance
06:36

Biomechanical Analysis Methods to Assess Professional Badminton Players' Lunge Performance

Published on: June 11, 2019

10.7K
Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography
04:06

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Published on: January 12, 2024

659

相关实验视频

Last Updated: Jul 12, 2025

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

3.8K
Biomechanical Analysis Methods to Assess Professional Badminton Players' Lunge Performance
06:36

Biomechanical Analysis Methods to Assess Professional Badminton Players' Lunge Performance

Published on: June 11, 2019

10.7K
Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography
04:06

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Published on: January 12, 2024

659

科学领域:

  • 人工智能的人工智能
  • 机器学习 机器学习
  • 可穿戴式传感器技术

背景情况:

  • 使用传感器识别人类活动正在推进人工智能.
  • 由于特征提取困难,识别像羽毛球这样的复杂活动具有挑战性.
  • 目前的卷积神经网络 (CNN) 方法与时间数据和全球信号理解扎.

研究的目的:

  • 开发一个先进的深度学习框架,用于基于传感器的羽毛球活动识别.
  • 解决现有的基于CNN的方法在捕捉时间动态和综合信号特征方面的局限性.
  • 提高从传感器数据识别复杂的人类活动的准确性和效率.

主要方法:

  • 提出了一个深度学习框架,集成卷积层,长短期记忆 (LSTM) 结构和自我注意力机制.
  • 该框架自动提取时间域中的本地传感器信号特征.
  • 利用LSTM处理羽毛球活动数据和自我注意力,以专注于重要信息.

主要成果:

  • 在使用单个传感器数据集识别37项羽毛球活动时,获得了97.83%的准确性.
  • 与现有的基于传感器的羽毛球活动识别方法相比,表现出卓越的性能.
  • 在减少培训时间和更快的融合方面展示了优势.

结论:

  • 拟议的深度学习框架有效地从传感器数据中识别复杂的羽毛球活动.
  • 结合CNN,LSTM和自我注意力,克服了传统方法的局限性.
  • 这种方法为基于传感器的活动识别提供了更准确,更有效和更快的解决方案.