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

A comprehensive review of ball detection techniques in sports.

PeerJ. Computer science·2025
Same author

Suboptimal distribution and utilization of antenatal care given bed Nets undermine pregnant women's protection in Benin: a prospective field study.

BMC public health·2025
Same author

Enhancing Security in 5G Edge Networks: Predicting Real-Time Zero Trust Attacks Using Machine Learning in SDN Environments.

Sensors (Basel, Switzerland)·2025
Same author

Lower Limb Movement during 10-Meter Walk Test: A Dataset with Inertial, Magnetic, and Temperature Sensors.

Scientific data·2025
Same author

Prediction of perinatal depression among women in Pakistan using Hybrid RNN-LSTM model.

PeerJ. Computer science·2025
Same author

Forecasting air pollution with deep learning with a focus on impact of urban traffic on PM10 and noise pollution.

PloS one·2024

相关实验视频

Updated: Jan 17, 2026

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

9.3K

通过机器学习增强人类活动识别:智能手机加速度计和磁力计数据的见解

Luis Augusto Silva Zendron1, Paulo Jorge Coelho2,3, Christophe Soares4,5

  • 1Department of Computer Science and Automation, Universidad de Salamanca, Salamanca, Spain.

PeerJ. Computer science
|September 24, 2025
PubMed
概括
此摘要是机器生成的。

这项研究使用智能手机传感器和机器学习来增强人类活动识别 (HAR). 新的方法实现了高精度,使HAR高效,可在移动设备上部署.

关键词:
加速计 加速计 加速计数据分析数据分析人类活动识别 (HAR)机器学习 机器学习磁力计 磁力计 磁力计传感器技术 传感器技术智能手机传感器的传感器

更多相关视频

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

5.3K
Home-Based Monitor for Gait and Activity Analysis
07:24

Home-Based Monitor for Gait and Activity Analysis

Published on: August 8, 2019

7.2K

相关实验视频

Last Updated: Jan 17, 2026

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

9.3K
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

5.3K
Home-Based Monitor for Gait and Activity Analysis
07:24

Home-Based Monitor for Gait and Activity Analysis

Published on: August 8, 2019

7.2K

科学领域:

  • 计算机科学 计算机科学
  • 人工智能的人工智能
  • 机器学习 机器学习

背景情况:

  • 人类活动识别 (HAR) 由于传感器和人工智能的进步,已经取得了重大进展.
  • 以前的研究使用智能手机传感器数据确定了HAR的基线结果.

研究的目的:

  • 实施和评估各种机器学习技术,以改善 HAR.
  • 在现有 HAR 数据集上分析神经网络,随机森林和其他模型的有效性.

主要方法:

  • 从智能手机传感器收集数据,然后进行清洁和正常化.
  • 功能提取和实施各种机器学习模型,包括神经网络和随机森林.
  • 利用非规范化数据和集成磁力计信号来提高性能.

主要成果:

  • 神经网络和随机森林模型显示出高效率.
  • 实现曲线下的面积 (AUC) 为98.42%,分类准确率为90.14%,F1得分为90.13%,精度为90.18%,回忆率为90.14%.
  • 性能优于早期的模型,计算成本降低,可与深度学习方法相比较.

结论:

  • 开发的方法是新的,高效的,适合实时移动应用.
  • 轻量级模型和可重复的视觉工作流程提高了部署能力.
  • 非规范化数据和磁力计信号的整合提高了HAR的性能.