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

Liver Damage in <i>Ctenopharyngodon idellus</i> Induced by Nanoplastics and Cadmium Exposure.

Biology·2026
Same author

Applicability boundaries and method-selection strategies for the CMC determination of pharmaceutical surfactants.

European journal of pharmaceutics and biopharmaceutics : official journal of Arbeitsgemeinschaft fur Pharmazeutische Verfahrenstechnik e.V·2026
Same author

Unlocking Zn-Ion Diffusion in Disordered Rocksalt Cathodes for Nonaqueous Zn-Ion Batteries.

Angewandte Chemie (International ed. in English)·2026
Same author

Anti-metastatic effects of emodin-8-O-β-D-glucopyranoside in breast cancer: Targeting EMT, MMPs, and angiogenesis.

Toxicology and applied pharmacology·2026
Same author

Global prevalence and associated factors of turnover intention among intensive care nurses: A systematic review and meta-analysis.

Intensive & critical care nursing·2026
Same author

Bioinformatics, expression, and immunogenicity analysis of MPXV A7 protein.

Protein expression and purification·2026

相关实验视频

Updated: Jul 28, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K

四个机器学习算法的比较,用于撞击前落检测系统.

Duojin Wang1,2, Zixuan Li3

  • 1Institute of Rehabilitation Engineering and Technology, University of Shanghai for Science and Technology, 516 Jungong Road, Shanghai, 200093, China. duojin.wang@usst.edu.cn.

Medical & biological engineering & computing
|May 31, 2023
PubMed
概括

这项研究使用智能鞋开发了一种低成本的摔倒检测系统. 该系统在撞击前准确地识别掉落,提供关键的干预时间以防止伤害.

关键词:
落检测 落检测 落检测多传感器的使用方法冲击前的影响.老年人 这些老年人可以穿戴的可穿戴设备.

更多相关视频

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.2K

相关实验视频

Last Updated: Jul 28, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.2K

科学领域:

  • 生物医学工程 生物医学工程
  • 可穿戴技术可穿戴技术
  • 机器学习用于医疗保健

背景情况:

  • 通过可穿戴传感器实时监测健康是一个重要的研究领域.
  • 跌倒检测系统对于预防伤害至关重要,尤其是在弱势群体中.
  • 现有的系统往往缺乏效率,负担能力或影响前检测能力.

研究的目的:

  • 开发和评估一个高效,低成本的落检测系统.
  • 为了比较四个机器学习算法的性能,用于撞击前落检测.
  • 评估系统在落发生之前提供及时干预的潜力.

主要方法:

  • 使用装有惯性和脚部压力传感器的鞋子设计了一个跌倒检测系统.
  • 四个机器学习算法 (K-Nearest Neighbors,支持矢量机,随机森林和BP神经网络) 被实现并进行了比较.
  • 包括灵敏度,特异性和准确性在内的性能指标被用于评估预冲击检测算法.

主要成果:

  • 与SVM和随机森林相比,K-最接近邻居 (KNN) 和BP神经网络算法表现出优异的性能.
  • 在KNN的研究中,KNN获得了98.8%的灵敏度,99.8%的特异性和99.7%的准确性.
  • BP神经网络实现了100%的灵敏度,99.8%的特异性和99.9%的准确性,这两种算法均为撞击前检测提供了460.95毫秒的领先时间.

结论:

  • 开发的基于鞋子的系统为实时摔倒检测提供了有效和负担得起的解决方案.
  • KNN和BP神经网络算法非常适合在撞击前发现落,从而能够及时干预.
  • 当与保护装置相结合时,该系统有可能显著减少与跌倒有关的伤害.