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

Cross-Modal Feature Adapter for Few-Shot Human Activity Recognition.

IEEE journal of biomedical and health informatics·2026
Same author

Motion prediction for leader manipulator of teleoperation system with large time delay based on inverse optimal control.

ISA transactions·2026
Same author

Dual-Modal Safety Framework for Robotic-Assisted Bronchoscopy via Endoscopic Vision and Haptic Feedback.

The international journal of medical robotics + computer assisted surgery : MRCAS·2026
Same author

Towards Interpretable Seizure Detection: An Excitation/Inhibition Dynamic Polynomial Network Framework for Electroencephalography.

Sensors (Basel, Switzerland)·2026
Same author

Human-in-the-Loop Control Framework for Robot-Mediated Error Augmentation Training Based on Muscle Synergy Assessment.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026
Same author

Design, Analysis, and Characterization of a Small-Scale High-Torque Magnetorheological Brake for Haptic Applications.

IEEE transactions on haptics·2026

相关实验视频

Updated: May 24, 2025

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

8.8K

学习传感器样本重量调整用于通过Meta学习进行动态早期退出活动识别.

Zenan Fu, Lei Zhang, Wenbo Huang

    IEEE journal of biomedical and health informatics
    |March 3, 2025
    PubMed
    概括

    这项研究引入了一种样本重量调整方法,以提高可穿戴设备上人类活动识别 (HAR) 深度神经网络的效率. 该方法根据样本难度动态调整培训重点,增强准确性-效率的权衡.

    科学领域:

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

    背景情况:

    • 动态早期退出策略通过允许更简单的样本在早期层退出来提高深度神经网络的效率.
    • 现有的方法经常忽视训练期间早期退出的动态性质,从而与测试时间的行为产生不匹配.
    • 由于计算限制,可穿戴设备上的人类活动识别 (HAR) 需要高效的模型.

    研究的目的:

    • 开发一种新的样本重量重定方法,用于在HAR中有效的活动推理.
    • 解决动态早期退出策略中的培训测试不匹配问题.
    • 在资源有限的可穿戴设备上提高HAR的准确性-效率权衡.

    主要方法:

    • 引入了采用重量预测网络的样本重量调整方法,以便在不同出口处动态调整每个样本的训练损失贡献.
    • 设计了一个基于元学习的优化目标,以共同训练重量预测网络和骨干网络.
    • 在UCI-HAR,WISDM和UniMiB-SHAR数据集上评估了该方法.

    主要成果:

    • 拟议的方法在预算批量分类和随时预测场景下持续改善了准确性-效率权衡.
    • 通过将测试时间的早期退出行为纳入训练管道,证明了性能的提高.
    • 在处理阶级不平衡的HAR问题方面表现出了自然的优势.

    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

    2.5K
    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

    相关实验视频

    Last Updated: May 24, 2025

    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

    8.8K
    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
    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

    结论:

    • 采样重权方法有效地弥合了动态早期退出HAR的培训-测试差距.
    • 这种方法为可穿戴HAR系统的计算效率和准确性提供了显著的改进.
    • 该方法是强大的和适应性的,特别是在不平衡的数据集和现实世界的部署场景.