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

Versatile Synthesis of Mesoporous Nanomaterials via Monomicelle-Directed Assembly.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

The Levels, Prevalence, and Related Factors of Toxic Leadership Among Nurses Outside the United States: A Systematic Review and Meta-Analysis.

The Journal of nursing administration·2026
Same author

Nursing Students' Pain Management Knowledge and Attitudes: A Systematic Review and Meta-Analysis.

Pain management nursing : official journal of the American Society of Pain Management Nurses·2026
Same author

Letter to the Editor: proposal of a novel model for identifying complete response and nonoperative management in DMMR colon cancer following neoadjuvant immunotherapy: a retrospective cohort study.

International journal of surgery (London, England)·2025
Same author

Machine learning for predicting burnout among healthcare workers: a systematic review and meta-analysis.

Contemporary nurse·2025
Same author

Moral resilience among nurses: A systematic review and meta-analysis.

Nursing ethics·2025

相关实验视频

Updated: Jun 21, 2025

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

9.4K

基于3D密集连接的异常行为识别.

Wei Chen1, Zhanhe Yu2, Chaochao Yang1

  • 1School of Electrical and Control Engineering, North China University of Technology, Beijing 100144, P. R. China.

International journal of neural systems
|July 16, 2024
PubMed
概括

本研究介绍了一种新的异常行为识别算法,使用3D密集连接进行增强的实时检测. 该方法通过快速识别与正常模式的偏差,以高的准确性和效率来提高城市安全.

关键词:
识别异常行为 识别异常行为在这里,GRU GRU GRU适应性软值值 适应性软值有密集的连接连接.多级别的学习多级别的学习.

更多相关视频

Measuring Connectivity in the Primary Visual Pathway in Human Albinism Using Diffusion Tensor Imaging and Tractography
13:26

Measuring Connectivity in the Primary Visual Pathway in Human Albinism Using Diffusion Tensor Imaging and Tractography

Published on: August 11, 2016

12.3K
Automatic Identification of Dendritic Branches and their Orientation
06:08

Automatic Identification of Dendritic Branches and their Orientation

Published on: September 17, 2021

1.9K

相关实验视频

Last Updated: Jun 21, 2025

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

9.4K
Measuring Connectivity in the Primary Visual Pathway in Human Albinism Using Diffusion Tensor Imaging and Tractography
13:26

Measuring Connectivity in the Primary Visual Pathway in Human Albinism Using Diffusion Tensor Imaging and Tractography

Published on: August 11, 2016

12.3K
Automatic Identification of Dendritic Branches and their Orientation
06:08

Automatic Identification of Dendritic Branches and their Orientation

Published on: September 17, 2021

1.9K

科学领域:

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

背景情况:

  • 识别异常行为对于安全和欺诈检测至关重要.
  • 深度卷积网络 (ConvNets) 是有前途的,但缺乏实时功能.
  • 现有的方法优先考虑准确性而不是速度,阻碍了立即威胁的识别.

研究的目的:

  • 开发一个实时异常行为识别算法.
  • 通过快速检测异常活动,增强城市公共安全.
  • 通过解决计算效率来改进现有的基于ConvNet的方法.

主要方法:

  • 提出了一个基于三维 (3D) 密集连接的算法.
  • 利用多实例学习策略来分类各种异常行为.
  • 采用密集连接模块和软值注意力机制来优化模型参数和计算效率.
  • 实施了注意分配,以减少冗余的顺序信息.

主要成果:

  • 在UCF犯罪数据集上实现了95.61%的识别准确度.
  • 与现有模型相比,在识别精度和处理速度方面表现出强的性能.
  • 成功降低了模型参数数量,提高了网络计算效率.

结论:

  • 提出的3D密集连接算法为实时异常行为识别提供了有效的解决方案.
  • 该方法平衡了高精度与提高计算效率,这对于公共安全应用至关重要.
  • 注意力机制和密集的连接有助于减轻冗余数据对性能的影响.