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

Exogenous Nitric Oxide Promotes the Growth and Cadmium Accumulation of Alfalfa (<i>Medicago sativa</i>) Seedlings Under Cadmium Stress.

Plants (Basel, Switzerland)·2025
Same author

Experimental Study on the Effect of Humidity on the Mechanical Properties of 3D-Printed Mechanical Metamaterials.

Polymers·2025
Same author

Protective Effect of Xihuang Pill on Immune Checkpoint Inhibitors-Related Myocarditis in a Mouse Model by Regulating the HIF-1 Signaling Pathway.

Journal of inflammation research·2025
Same author

<i>Epimedii Folium</i> flavonoids: A double-edged sword effect on the liver, a dual exploration of efficacy and toxicity.

Journal of pharmaceutical analysis·2025
Same author

Lignosulfonate supported CeO<sub>2</sub>/Co<sub>3</sub>O<sub>4</sub> nanocomposites with dual enzyme activity for colorimetric detection of catechol and smartphone-assisted visual ratiometric analysis.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2025
Same author

Emerging nutritional potential of edible-medicinal homologous coix lacryma-jobi seed-derived exosomes for treatment of ulcerative colitis.

International journal of biological macromolecules·2025

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

一个基于深度学习的空中目标意图数据扩展和识别模型.

Bo Cao1, Qinghua Xing2, Longyue Li3

  • 1Graduate School, Air Force Engineering University, Xi'an, 710051, China.

Scientific reports
|April 22, 2025
PubMed
概括

本研究引入了一个深度学习模型 (IDERDL),通过解决数据稀缺性和时间特征提取来改善空中目标意图识别. IDERDL模型达到98.73%的准确性,显著提高了战场情境意识.

关键词:
否认扩散的概率模型.扩展的因果卷积.图表注意力网络 图表注意力网络意图的认可意图的认可情境认知情况认知.

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

430
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
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

430
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:

  • 人工智能的人工智能
  • 航空航天工程 航空航天工程
  • 军事科学 军事科学

背景情况:

  • 在现代空中作战中,识别空中目标意图对于战场情境意识至关重要.
  • 由于数据稀缺和时间特征提取不足,现有的方法面临挑战.

研究的目的:

  • 提出一种新的深度学习模型,即基于深度学习的意图数据扩展和识别 (IDERDL),以解决数据稀缺问题,并改进用于空中目标意图识别的时间特征提取.

主要方法:

  • 开发了一个意图数据生成模型,使用一个无声扩散模型,并改进了知识蒸以进行加速采样.
  • 构建了一个带有扩张因果卷积的时块,以增强时特征提取.
  • 集成了一个图表注意力机制来分析特征关系,输入软max层进行分类.

主要成果:

  • 拟议的IDERDL模型实现了98.73%的高意图识别精度.
  • 与现有的空中目标意图识别方法相比,证明了卓越的性能.
  • 在这个领域有效地解决了数据稀缺和时间特征提取方面的挑战.

结论:

  • 通过独特考虑数据稀缺性和时间性,IDERDL模型在战术意图识别方面取得了重大进展.
  • 这些发现对改善军事应用中的空中目标意图识别能力具有高度意义.