Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Genome-wide association analysis and candidate gene identification for plant height in Shanxi local foxtail millet varieties.

TAG. Theoretical and applied genetics. Theoretische und angewandte Genetik·2026

Same author

Comprehensive Analysis of the <i>TaABCB</i> Gene Family and the Role of <i>TaABCB7</i> in the Phosphate Starvation Response in Wheat.

Biology·2025

Same author

Genome-wide identification and expression analysis of the MBD gene family in Broomcorn millet (Panicum miliaceum) and its response to abiotic stress.

BMC genomics·2025

Same author

The complete genome assembly of Astragalus membranaceus: enabling more accurate genetic research.

GigaScience·2025

Same author

Telomere-to-telomere genome of common bean (Phaseolus vulgaris L., YP4).

GigaScience·2025

Same author

Telomere-to-telomere genome assembly of sorghum.

Scientific data·2024

Search research articles

相关实验视频

Updated: Jun 14, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

基于深度学习的物联网预警系统用于检测异常的子行为.

Hongshuai Qin¹, Minya Cai¹, Huibin Qin¹

¹School of Computer Science, Hangzhou Dianzi University, Hangzhou 310018, China.

Sensors (Basel, Switzerland)

|August 29, 2024

概括

长时间使用电子设备会导致部问题. 一个新的深度学习模型,NABNet,通过姿势估计和物体检测检测出异常的子行为,实现94.13%的早期干预准确度.

科学领域:

生物医学工程生物医学工程
计算机科学计算机科学
医疗信息学医疗信息学

背景情况:

久坐不动的生活方式和长时间使用电子设备有助于部疼痛和压力损伤.
早期发现和纠正异常的部姿势对于预防严重的身体健康风险至关重要.
现有的通用物体探测器无法识别微妙的,有害的部行为.

研究的目的:

开发一种基于深度学习的系统,用于检测异常的子行为.
提出NABNet,一个新的模型,集成YOLOv5s对象检测和轻量级OpenPose进行详细的部行为分析.
通过物联网系统实现远程监控和实时报警,通过物联网系统对异常的部姿势进行报警.

主要方法:

通过结合YOLOv5s用于对象检测和轻量级OpenPose用于姿势估计来开发NABNet.
从全球到地方的角度提取了详细的部行为特征.
分析了部的角度,以检测异常的行为模式.
在云端和边缘设备上部署了基于NABNet的系统,以提供全面的物联网解决方案.

主要成果:

在NABNet系统证明了有效检测异常的部行为.
该系统在云平台上成功发出了警报.

关键词:

物联网系统物联网系统物联网系统.这是YOLOv5s.检测异常行为检测异常行为轻量级的模型轻量级的模型.构成估计估计的估计.

更多相关视频

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

相关实验视频

Last Updated: Jun 14, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

在检测异常的部姿势方面达到94.13%的最高准确率.

验证了物联网系统对实时监控的有效性.

结论:

拟议的NABNet模型提供了一个强大的解决方案,用于识别有害的部行为.
综合物联网系统为远程监控和早期干预提供了实用方法.
这项技术有可能减轻与长时间屏幕相关的健康风险.