Jove
Visualize
联系我们

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

EEG-based harmful brain activity classification using deep learning and feature fusion.

Scientific reports·2026
Same author

GGAR: gradient guided adaptive regularization enhances deep learning classification of brassica species using codon usage bias.

BMC bioinformatics·2026
Same author

A robust deep learning approach for impulse noise filtering using hybrid auto-encoder with fuzzy median filter.

PloS one·2026
Same author

BAAR: A framework for blockchain-based anonymous and revocable user authentication scheme.

PloS one·2026
Same author

Ensemble Deep Learning-Based High-Precision Framework for Breast Cancer Detection from Histopathological Images.

Diagnostics (Basel, Switzerland)·2026
Same author

Unveiling the black box: Explainable transfer learning for ocular disorder diagnosis.

Digital health·2026
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

相关实验视频

Updated: May 10, 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

2.4K

使用深度学习技术对人类活动进行智能识别.

Shazab Bashir1,2, Arfan Jaffar1,2, Muhammad Rashid3

  • 1Faculty of Computer Science & Information Technology, The Superior University, Lahore, Pakistan.

PloS one
|April 24, 2025
PubMed
概括

这项研究使用一组深度学习模型在视频中增强了人为动作识别 (HAR). 先进的组合方法实现了卓越的准确性,为医疗保健和监控应用制定了新的标准.

更多相关视频

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
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.3K

相关实验视频

Last Updated: May 10, 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

2.4K
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
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.3K

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 机器学习 机器学习

背景情况:

  • 人类动作识别 (HAR) 对于分析视频中的人类行为至关重要.
  • 深度学习框架为HAR任务提供了强大的工具.
  • 现有的方法可以改进,以提高准确性和可靠性.

研究的目的:

  • 在RGB视频中使用深度学习来调查和增强人类行动识别 (HAR).
  • 开发一个整体模型,集成3D-AlexNet-RF和InceptionV3 Google-Net,以提高HAR准确度.
  • 评估整体框架对各种人类行为HMDB51数据集的表现.

主要方法:

  • 使用了一种组合方法,将3D-AlexNet-RF和InceptionV3 Google-Net模型的预测结合起来.
  • 在HMDB51数据集上的训练膨胀3D (I3D) 视频分类器.
  • 采用投票或平均技术,将单个模型预测合并为最终分类.

主要成果:

  • 在HMDB51数据集上实现了99.54%的总准确性.
  • 在包括精度 (97.94%),回忆 (97.94%) 和F1-Score (97.88%) 在内的各种指标上表现出高绩效.
  • 合奏模型在HAR任务中被证明是非常有效和可靠的.

结论:

  • 拟议的合奏模型显著提高了HAR的性能.
  • 这种方法为医疗保健,监视和人机交互的应用设定了新的标准.
  • 多层组合显示出增强可穿戴技术识别的潜力.