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

Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition.

Sensors (Basel, Switzerland)·2024
Same author

Intelligent Care Management for Diabetic Foot Ulcers: A Scoping Review of Computer Vision and Machine Learning Techniques and Applications.

Journal of diabetes science and technology·2023
Same author

The Lifespan of Human Activity Recognition Systems for Smart Homes.

Sensors (Basel, Switzerland)·2023
Same author

A TTFS-based energy and utilization efficient neuromorphic CNN accelerator.

Frontiers in neuroscience·2023
Same author

Complex Deep Neural Networks from Large Scale Virtual IMU Data for Effective Human Activity Recognition Using Wearables.

Sensors (Basel, Switzerland)·2021
Same author

A Real-Time Eating Detection System for Capturing Eating Moments and Triggering Ecological Momentary Assessments to Obtain Further Context: System Development and Validation Study.

JMIR mHealth and uHealth·2020

相关实验视频

Updated: Jun 22, 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

8.9K

使用图表在智能家居中执行有效的基于传感器的人类活动识别.

Srivatsa P1, Thomas Plötz1

  • 1Georgia Institute of Technology, Atlanta, GA 30332, USA.

Sensors (Basel, Switzerland)
|June 27, 2024
PubMed
概括

这项研究引入了用于智能家居的人类活动识别 (HAR) 的图形引导神经网络,克服了对预先细分的传感器数据的需求. 这种新的方法有效地学习传感器关系,提高了现实世界的应用性.

科学领域:

  • 计算机科学 计算机科学
  • 人工智能的人工智能
  • 无处不在的计算 无处不在的计算

背景情况:

  • 人类活动识别 (HAR) 对智能家居,环境智能和辅助生活至关重要.
  • 现有的HAR系统面临着数据变化,稀疏性和噪声等挑战.
  • 当前最先进的HAR方法需要预先对传感器数据进行细分,从而限制了现实世界的部署.

研究的目的:

  • 为智能家居中的 HAR 提出一种新的图形引导的神经网络方法.
  • 为了克服现有的HAR系统中预细分的局限性.
  • 为了实现连续传感器数据流的自动分析,而无需人工干预.

主要方法:

  • 开发了一个以图形指导的神经网络,可以学习传感器之间的明确协同发射关系.
  • 利用数据驱动的方法来学习表达式图形结构,代表智能家居传感器网络.
  • 采用注意力机制和节点嵌入的层次聚合,将离散的传感器测量映射到特征空间.

主要成果:

  • 拟议的图形引导神经网络在CASAS数据集上显著优于最先进的HAR方法.
  • 在多个数据集中展示了卓越的性能,表明了稳定性和有效性.
  • 与现有方法相比,取得了很大的改进空间.
关键词:
人类活动的认可 人类活动的认可以人为中心的计算是以人为中心的计算.机器学习是机器学习.模式识别 模式识别 模式识别智能家居是一个智能家居.无处不在的和移动计算.

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

2.7K
Methodology for Establishing a Community-Wide Life Laboratory for Capturing Unobtrusive and Continuous Remote Activity and Health Data
11:21

Methodology for Establishing a Community-Wide Life Laboratory for Capturing Unobtrusive and Continuous Remote Activity and Health Data

Published on: July 27, 2018

8.2K

相关实验视频

Last Updated: Jun 22, 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

8.9K
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

2.7K
Methodology for Establishing a Community-Wide Life Laboratory for Capturing Unobtrusive and Continuous Remote Activity and Health Data
11:21

Methodology for Establishing a Community-Wide Life Laboratory for Capturing Unobtrusive and Continuous Remote Activity and Health Data

Published on: July 27, 2018

8.2K

结论:

  • 这种新型的图形引导神经网络有效地执行HAR,而不需要预先对传感器数据进行细分.
  • 这种方法提高了HAR系统在现实世界智能家居环境中的实际适用性.
  • 这些发现代表了迈向更自主和可靠的智能家居技术的重要一步.