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

Force Classification01:22

Force Classification

Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...

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

Sensing In Exergames for Efficacy and Motion Quality: Scoping Review of Recent Publications.

JMIR serious games·2024
Same author

Assessing the Accuracy of Smartwatch-Based Estimation of Maximum Oxygen Uptake Using the Apple Watch Series 7: Validation Study.

JMIR biomedical engineering·2024
Same author

Give Me a Sign: Using Data Gloves for Static Hand-Shape Recognition.

Sensors (Basel, Switzerland)·2023
Same author

Recognizing Full-Body Exercise Execution Errors Using the Teslasuit.

Sensors (Basel, Switzerland)·2021
Same author

Quality Criteria for Serious Games: Serious Part, Game Part, and Balance.

JMIR serious games·2020

相关实验视频

Updated: Jun 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

8.9K

基于IMU的健身活动识别使用CNNs进行时间序列分类.

Philipp Niklas Müller1, Alexander Josef Müller1, Philipp Achenbach1

  • 1Serious Games Group, Technical University of Darmstadt, 64289 Darmstadt, Germany.

Sensors (Basel, Switzerland)
|February 10, 2024
PubMed
概括

卷积神经网络 (CNN) 显示出使用惯性测量单位 (IMU) 的移动健身活动识别 (FAR) 的前景. 选择性移除传感器改善了CNN的性能,新型调量-FCN实现了99.86%的准确性.

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:

  • 移动健身应用程序依赖于通过惯性测量单元 (IMU) 准确的活动跟踪.
  • 卷积神经网络 (CNN) 在时间序列分类方面表现出色,但由于数据稀缺和活动相似性,在健身活动识别 (FAR) 中面临挑战.
  • 人类活动识别 (HAR) 任务通常使用传统的机器学习 (ML) 方法.

研究的目的:

  • 使用IMU数据评估CNN对健身活动识别 (FAR) 的有效性.
  • 确定输入数据大小和传感器数量对FAR中CNN性能的影响.
  • 将CNN的性能与FAR的传统ML方法进行比较.

主要方法:

  • 调整了三种现有的CNN架构,并为FAR开发了一种新的Scaling-FCN.
  • 实施了预处理管道,并从20名参与者那里收集了运行练习数据集.
  • 在收集的数据集上评估了四个CNN和三种传统的ML方法 (包括支持矢量机 - SVM).

主要成果:

  • 所有的CNN架构都实现了超过94%的测试准确度.
  • 传统的ML方法,特别是SVM,在默认场景中表现优于CNN (99.00 ± 0.34%准确度).
关键词:
活动识别活动识别.卷积神经网络是一种卷积神经网络.深度学习是一种深度学习.惯性测量单位是一种惯性测量单位.剩余神经网络 剩余神经网络研究研究研究研究研究.传统的机器学习.

更多相关视频

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
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

相关实验视频

Last Updated: Jun 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

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
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
  • 减少传感器提高了CNN性能,使用单脚传感器,缩放FCN达到99.86 ± 0.11%的准确性.

    • 结论:

    • CNNs适合使用IMU数据进行健身活动识别 (FAR).
    • 选择性传感器减少可以显著提高CNN在FAR的性能.
    • 传统的ML方法仍然具有竞争力,尤其是在充足,有利的输入数据的情况下.