Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

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

Automatic Recognition of Dual-Component Radar Signals Based on Deep Learning.

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
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
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

This study introduces TFGM-RMNet, a novel deep learning framework for radar signal recognition. It achieves high accuracy even at low signal-to-noise ratios (SNR), outperforming existing methods.

Area of Science:

  • Electrical Engineering
  • Artificial Intelligence
  • Signal Processing

Background:

  • Increasing electromagnetic signal density and complexity challenge radar signal recognition.
  • Low signal-to-noise ratios (SNR) significantly reduce the accuracy of common time-frequency transformation (TFT) and convolutional neural network (CNN) based frameworks.

Purpose of the Study:

  • To propose a novel dual-component radar signal recognition framework, TFGM-RMNet, to improve recognition accuracy under low SNR conditions.
  • To develop an end-to-end deep learning framework that integrates time-frequency feature learning and robust classification.

Main Methods:

  • A deep time-frequency generation module (TFGM) learns basis functions to extract time-frequency (TF) features, outputting time-frequency representations (TFRs).
  • A ResNet combined with cascaded multi-head self-attention (MHSA) extracts local and global features from TFRs.
Keywords:
convolutional neural networksdual-component pulse-internal modulationmulti-head self-attentionmulti-label learningpulse-internal modulation classification

More Related Videos

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

Related Experiment Videos

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
  • Multi-label classification is used for modulation format prediction, with TFT integrated into TFGM for end-to-end operation.

    • Main Results:

    • The TFGM-RMNet framework achieves near 100% average recognition accuracy when SNR > -8 dB.
    • It maintains 97% accuracy at an SNR of -10 dB.
    • Performance surpasses existing algorithms like DCNN-RAMIML, DCNN-MLL, and DCNN-MIML under low SNR.

    Conclusions:

    • The proposed TFGM-RMNet framework effectively enhances radar signal recognition accuracy, particularly in low SNR environments.
    • Integrating TFGM and a Transformer-based residual network offers a robust, end-to-end solution for complex electromagnetic signal analysis.
    • This approach overcomes limitations of traditional TFT-CNN methods, providing superior performance and accuracy.