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

Association Areas of the Cortex01:21

Association Areas of the Cortex

5.5K
Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
5.5K

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

Strain-Engineered Monolithic Multi-Band LEDs for Simultaneous Short-Wavelength and Mid-Wavelength Infrared Emission.

Advanced materials (Deerfield Beach, Fla.)·2025
Same author

Optimizing InAsPSb/InAsP cladding structures to control carrier overflow and enhance emission in multiple quantum well LEDs.

Nanoscale·2025
Same author

Inhibition of PRC2 enables self-renewal of blastoid-competent naive pluripotent stem cells from chimpanzee.

Cell stem cell·2025
Same author

An Intelligent Ball Bearing Fault Diagnosis System Using Enhanced Rotational Characteristics on Spectrogram.

Sensors (Basel, Switzerland)·2024
Same author

Comparison of microbial molecular diagnosis efficiency within unstable template metagenomic DNA samples between qRT-PCR and chip-based digital PCR platforms.

Genomics & informatics·2024
Same author

A Modified Aquila-Based Optimized XGBoost Framework for Detecting Probable Seizure Status in Neonates.

Sensors (Basel, Switzerland)·2023

相关实验视频

Updated: Jul 24, 2025

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

3.9K

人类活动识别使用基于注意力机制的深度学习特征组合

Morsheda Akter1, Shafew Ansary1, Md Al-Masrur Khan2

  • 1Department of Electronics Engineering, Dong-A University, Busan 49315, Republic of Korea.

Sensors (Basel, Switzerland)
|July 8, 2023
PubMed
概括
此摘要是机器生成的。

本研究引入了一种新的深度学习方法,用于使用卷积神经网络 (CNN) 和注意力机制进行人类活动识别 (HAR). 该方法在多个数据集上实现了高精度,提高了HAR系统的性能.

关键词:
注意力机制注意力机制深度学习是一种深度学习.功能组合 功能组合 功能组合人类行动承认承认

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

583
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K

相关实验视频

Last Updated: Jul 24, 2025

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

3.9K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

583
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K

科学领域:

  • 计算机科学 计算机科学
  • 人工智能的人工智能
  • 信号处理 信号处理

背景情况:

  • 人类活动识别 (HAR) 对医疗保健,老年护理和监测至关重要.
  • 深度学习 (DL) 模型,特别是卷积神经网络 (CNN),擅长自动从传感器数据中提取 HAR 的特征.
  • 现有的HAR方法通常依赖于手工制作的特征,这些特征可能是复杂和低于最佳的.

研究的目的:

  • 为增强人类活动识别 (HAR) 提出一种新的深度学习方法.
  • 通过结合多个阶段的功能和整合注意力机制来提高HAR的准确性.
  • 使用卷积神经网络 (CNN) 和CBAM模块开发基于传感器的HAR的通用模型结构.

主要方法:

  • 使用卷积神经网络 (CNN) 进行HAR,将原始传感器信号处理为光谱图.
  • 实施了一种新的方法,将多个卷积阶段的特征结合起来,以获得更丰富的表示.
  • 集成了一个卷积块注意模块 (CBAM) 来完善特征提取和提高模型准确性.

主要成果:

  • 拟议的CNN模型实现了高分类准确率:KU-HAR上的96.86%,UCI-HAR上的93.48%,WISDM上的93.89%.
  • 与之前的HAR方法相比,该方法在多个评估指标中显示出更高的性能.
  • 整合多阶段特征组合和注意力机制的整合对HAR有效.

结论:

  • 开发的深度学习模型为基于传感器的人类活动识别提供了一个全面而有能力的解决方案.
  • 新的特征提取技术,利用多阶段特征组合和注意力,显著提高了HAR准确性.
  • 这种通用模型结构显示了在医疗保健和监测中的各种HAR应用的前景.