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

相关实验视频

Updated: May 10, 2025

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

428

基于深度学习的双组件雷达信号的自动识别.

Zeyu Tang1, Hong Shen2, Chan-Tong Lam1

  • 1Faculty of Applied Sciences, Macao Polytechnic University, Macao SAR 999078, China.

Sensors (Basel, Switzerland)
|April 28, 2025
PubMed
概括

本研究介绍了TFGM-RMNet,这是一个用于雷达信号识别的新型深度学习框架. 它即使在信号噪声比 (SNR) 低的情况下也能达到高精度,超过现有方法.

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

A Convolutional-Transformer Residual Network for Channel Estimation in Intelligent Reflective Surface Aided MIMO Systems.

Sensors (Basel, Switzerland)·2025
Same author

Attention-Based Transfer Enhancement Network for Cross-Corpus EEG Emotion Recognition.

Sensors (Basel, Switzerland)·2025
Same author

Adaptive Damping Log-Domain Message-Passing Algorithm for FTN-OTFS in V2X Communications.

Sensors (Basel, Switzerland)·2025
Same author

Effective Detection of Cloud Masks in Remote Sensing Images.

Sensors (Basel, Switzerland)·2024
Same author

Energy-Efficient Cooperative Spectrum Sensing Using Machine Learning Algorithm.

Sensors (Basel, Switzerland)·2022
Same author

Differential gene expression in ovaries of Qira black sheep and Hetian sheep using RNA-Seq technique.

PloS one·2015

科学领域:

  • 电气工程 电气工程
  • 人工智能的人工智能
  • 信号处理 信号处理

背景情况:

  • 电磁信号密度和复杂度的增加挑战了雷达信号识别.
  • 低信号噪声比 (SNR) 显著降低了基于常见时间频率转换 (TFT) 和卷积神经网络 (CNN) 的框架的准确性.

研究的目的:

  • 提出一种新的双组件雷达信号识别框架,TFGM-RMNet,以提高在低SNR条件下的识别精度.
  • 开发一个端到端的深度学习框架,集成时间频率特征学习和强大的分类.

主要方法:

  • 一个深度时间频率生成模块 (TFGM) 学习基本函数来提取时间频率 (TF) 特性,输出时间频率表示 (TFR).
  • 一个ResNet与级联式多头自我注意 (MHSA) 结合,从TFR中提取本地和全球特征.
  • 多标签分类用于调制格式预测,TFT集成到TFGM进行端到端操作.

主要成果:

  • 在SNR> -8dB时,TFGM-RMNet框架实现了接近100%的平均识别准确性.
  • 它保持97%的准确性,SNR为-10dB.
  • 在低SNR的情况下,性能超过了现有的算法,如DCNN-RAMIML,DCNN-MLL和DCNN-MIML.

结论:

  • 拟议的TFGM-RMNet框架有效地提高了雷达信号识别精度,特别是在低SNR环境中.
  • 集成TFGM和基于变压器的残余网络为复杂的电磁信号分析提供了强大的端到端解决方案.
  • 这种方法克服了传统TFT-CNN方法的局限性,提供了卓越的性能和准确性.
关键词:
卷积神经网络是一种卷积神经网络.双组件脉冲内部调制双组件脉冲内部调制多头自我注意的多头自我注意.多标签学习多标签学习脉冲内部调制的分类.

更多相关视频

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
11:54

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

9.2K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

8.9K

相关实验视频

Last Updated: May 10, 2025

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

428
Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
11:54

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

9.2K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

8.9K