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: Oct 4, 2025

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

9.4K

LPI Radar Waveform Recognition Based on Neural Architecture Search.

Zhiyuan Ma1, Wenting Yu1, Peng Zhang1

  • 1Academy of Electronic Engineering, Naval University of Engineering, Wuhan, China.

Computational Intelligence and Neuroscience
|February 3, 2022
PubMed
Summary

This study introduces neural architecture search (NAS) for radar waveform recognition, eliminating reliance on transfer learning. A novel flexible-DARTS method achieves 79.2% accuracy for 15 radar types, improving generalization.

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

PAPS1-associated alternative polyadenylation changes correlate with pollen development and flowering time in Arabidopsis.

Plant physiology·2026
Same author

Onset of extensive human fire use 50,000 y ago.

Proceedings of the National Academy of Sciences of the United States of America·2025
Same author

The bs-YHEDA peptide protects the brains of senile mice and thus recovers intelligence by reducing iron and free radicals.

Free radical biology & medicine·2022
Same author

LPI Radar Waveform Recognition Based on Features from Multiple Images.

Sensors (Basel, Switzerland)·2020
Same author

Simulation of wavelength conversion based on integrated saturable absorber.

Applied optics·2010
Same author

Traditional Chinese medicine in the treatment of rheumatoid arthritis: a general review.

Rheumatology international·2010

Area of Science:

  • Artificial Intelligence
  • Signal Processing
  • Radar Systems

Background:

  • Deep learning classifiers for radar waveform recognition often use transfer learning with pretrained convolutional neural networks.
  • While transfer learning mitigates overfitting, transferred models can be redundant and lack generalization.
  • Achieving high generalization ability without transfer learning is a key challenge in intelligent radar recognition.

Purpose of the Study:

  • To introduce neural architecture search (NAS) for automatic classifier design in radar waveform recognition.
  • To develop a novel NAS method, flexible-DARTS, for improved generalization.
  • To evaluate the performance of NAS-designed classifiers against existing methods.

Main Methods:

  • Utilized differentiable architecture search (DARTS), an innovative NAS technology, to automatically design classifiers for 15 low probability intercept radar waveforms.

More Related Videos

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform
06:25

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Published on: February 12, 2014

8.6K
Harmonic Radar Tags for Insect Tracking: Lightweight, Low-cost, and Accessible
14:44

Harmonic Radar Tags for Insect Tracking: Lightweight, Low-cost, and Accessible

Published on: May 13, 2025

1.2K

Related Experiment Videos

Last Updated: Oct 4, 2025

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

9.4K
Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform
06:25

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Published on: February 12, 2014

8.6K
Harmonic Radar Tags for Insect Tracking: Lightweight, Low-cost, and Accessible
14:44

Harmonic Radar Tags for Insect Tracking: Lightweight, Low-cost, and Accessible

Published on: May 13, 2025

1.2K
  • Proposed flexible-DARTS, incorporating an auxiliary classifier in the middle layer to enhance classifier generalization.
  • Compared the performance of the flexible-DARTS model with related work in practical applications.

    • Main Results:

    • The flexible-DARTS method demonstrated superior performance in designing well-generalized classifiers compared to standard DARTS.
    • The developed model achieved an accuracy rate of 79.2% for recognizing 15 types of radar waveforms at a signal-to-noise ratio (SNR) of -9 dB.
    • Simulations confirmed the effectiveness of the proposed flexible-DARTS approach for radar waveform recognition.

    Conclusions:

    • Neural architecture search (NAS), specifically flexible-DARTS, offers a viable alternative to transfer learning for radar waveform classification.
    • The flexible-DARTS method significantly improves the generalization ability of radar waveform classifiers.
    • The proposed approach effectively enhances intelligent recognition capabilities in radar systems.