Jove
Visualize
联系我们

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

Highly Sensitive Hybridization Chain Reaction-Based miRNA Detection Technology Using Diffusivity Analysis of Fluorescent Probe-Modified miRNA Particles.

Sensors (Basel, Switzerland)·2026
Same author

Clinical Evaluation of Initial Experiences With the Qualitative Dual Detection of Core Antigen and Antibodies Immunoassay for Hepatitis C Virus Screening Test.

Hepatology research : the official journal of the Japan Society of Hepatology·2025
Same author

Sensor-Based Activity Recognition Using Frequency Band Enhancement Filters and Model Ensembles.

Sensors (Basel, Switzerland)·2023
Same author

Use of mathematical modeling and its inverse analysis for precise assessment of pesticide dissipation in a paddy environment.

Journal of pesticide science·2022
Same author

Three host peculiarities of a cycloalkane-based micelle toward large metal-complex guests.

Nature communications·2020
Same author

Inverse modeling of laboratory experiment to assess parameter transferability of pesticide environmental fate into outdoor experiments under paddy test systems.

Pest management science·2020
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

在基于传感器的人类活动识别中的基于细分的无监督学习方法.

Koki Takenaka1, Kei Kondo1, Tatsuhito Hasegawa1

  • 1Graduate School of Engineering, University of Fukui, Fukui 910-8507, Japan.

Sensors (Basel, Switzerland)
|October 28, 2023
PubMed
概括

这项研究引入了一种新的无监督深度学习方法,用于使用加速度计数据进行人类活动识别 (HAR). 该方法有效地提取了通用特征,证明了对传感器采样频率的稳定性.

科学领域:

  • 计算机科学 计算机科学
  • 生物医学工程 生物医学工程
  • 机器学习 机器学习

背景情况:

  • 基于传感器的人类活动识别 (HAR) 对于行为分析至关重要,特别是在医疗保健领域.
  • 传统的HAR方法依赖于机器学习,而深度学习则提供自动特征提取,但需要大量的标记数据.
  • 为深度学习模型标记数据是劳动密集型和昂贵的.

研究的目的:

  • 提出基于细分的无监督深度学习方法,用于使用加速度计数据的HAR.
  • 通过专注于活动细分点而不是标签来降低数据注释成本.
  • 开发一个强大的HAR系统,适应各种情况和传感器数据特征.

主要方法:

  • 为HAR开发了一个基于细分的无监督深度学习方法.
  • 提出了一种数据收集方法,只需要开始,改变和结束点的注释.
  • 创建了一个基于细分的新型SimCLR与SDFD相结合,用于特征表示学习.

主要成果:

  • 证明拟议的组合方法获得了通用的特征表示.
  • 通过转移学习展示了通过传感器数据采样频率的方法的稳定性.
  • 验证了无监督特征学习对HAR的有效性.
关键词:
加速度计传感器数据人类活动的认可 人类活动的认可细分数据 细分数据 分段数据无监督的代表学习学习.

更多相关视频

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

8.9K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K

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
Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

8.9K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K

结论:

  • 提出的基于细分的无监督深度学习方法为HAR提供了有效的解决方案.
  • 这种方法可以显著降低注释成本,同时保持高性能.
  • 该方法对需要适应性强的人类活动识别的现实应用具有前景.