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

Machine Learning-Based Toothbrushing Region Recognition Using Smart Toothbrush Holder and Wearable Sensors.

Biosensors·2025
Same author

Inertial Measurement Unit-Based Frozen Shoulder Identification from Daily Shoulder Tasks Using Machine Learning Approaches.

Sensors (Basel, Switzerland)·2024
Same author

A Man With Epigastric Pain.

Annals of emergency medicine·2024
Same author

An Analysis of Fluid Intake Assessment Approaches for Fluid Intake Monitoring System.

Biosensors·2024
Same author

Multiphase Identification Algorithm for Fall Recording Systems Using a Single Wearable Inertial Sensor.

Sensors (Basel, Switzerland)·2021
Same author

Automatic Functional Shoulder Task Identification and Sub-task Segmentation Using Wearable Inertial Measurement Units for Frozen Shoulder Assessment.

Sensors (Basel, Switzerland)·2020

相关实验视频

Updated: May 14, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.6K

数据增强方法的性能分析,以改进基于手腕的摔倒检测系统.

Yu-Chen Tu1, Che-Yu Lin1, Chien-Pin Liu1

  • 1Department of Biomedical Engineering, National Yang Ming Chiao Tung University, Taipei City 112, Taiwan.

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

这项研究使用数据增强增强了对老年人的基于手腕的摔倒检测. 条件扩散模型显著提高了准确性,即使数据有限,确保可靠的下降警报.

科学领域:

  • 老年学是指老年学的学科.
  • 生物医学工程 生物医学工程
  • 人工智能的人工智能

背景情况:

  • 社会老龄化增加老年人下降的风险,导致严重的身体,心理和财务后果.
  • 有效的跌倒检测系统对于及时发出警报和减轻跌倒相关伤害至关重要.
  • 基于手腕的系统提供便利性,但由于复杂的手动模拟和数据限制,面临性能挑战.

研究的目的:

  • 研究和比较各种数据增强技术,以改进基于深度学习的手腕式摔倒检测系统.
  • 解决落检测数据集中阶级不平衡和数据稀缺的常见问题.
  • 确定最有效的数据增强方法,以提高老年人跌倒检测的性能.

主要方法:

  • 分析多种数据增强方法,应用于用于摔倒检测的手腕传感器数据.
  • 在增强数据集上训练的深度学习模型的实施.
  • 使用诸如F1分数等指标评估系统性能,特别是在训练数据有限的情况下.

主要成果:

  • 条件扩散模型作为数据增强技术表现出卓越的性能.
  • 当模型仅使用25%的原始数据进行训练时,F1得分提高了6.58%.
  • 生成的合成数据保持了高质量,有效地补充了有限的真实世界数据.
关键词:
数据增强数据增强深度学习技术深度学习技术可穿戴式传感器传感器基于手腕的跌倒检测仪

更多相关视频

Author Spotlight: Innovations in iTUG Test for Enhanced Risk Assessment and Cognitive Insights
05:26

Author Spotlight: Innovations in iTUG Test for Enhanced Risk Assessment and Cognitive Insights

Published on: October 25, 2024

802
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

2.5K

相关实验视频

Last Updated: May 14, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.6K
Author Spotlight: Innovations in iTUG Test for Enhanced Risk Assessment and Cognitive Insights
05:26

Author Spotlight: Innovations in iTUG Test for Enhanced Risk Assessment and Cognitive Insights

Published on: October 25, 2024

802
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

2.5K

结论:

  • 条件扩散模型是基于手腕的摔倒检测系统中数据增强的高效方法.
  • 这种方法显著提高了跌倒检测的准确性,特别是在处理稀缺数据时,这使得它成为老年人跌倒监测的理想选择.
  • 高质量的合成数据生成可以克服数据的局限性,提高深度学习模型的可靠性,用于降落检测.