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 Concept Videos

Force Classification01:22

Force Classification

2.2K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
2.2K
Classification of Signals01:30

Classification of Signals

1.3K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.3K
Survival Tree01:19

Survival Tree

374
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
374

You might also read

Related Articles

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

Sort by
Same author

Artificial intelligence for carbon emissions management: advances, challenges, and future directions across monitoring, prediction, and reduction.

Carbon balance and management·2026
Same author

A thin robot made of flexible electronics for in-situ machining and inspection of large structures.

Nature communications·2026
Same author

Reagent-Free Molecular Pendulum Biosensor with Antibody-Aptamer Dual Recognition for Protein Analysis.

ACS sensors·2026
Same author

Interfacial toughening via S<sub>8</sub>@C<sub>60</sub> for high-performance inverted perovskite solar cells.

Science bulletin·2026
Same author

Micromechanical characteristics of compression densification of spent mushroom residue biomass based on DEM.

Scientific reports·2026
Same author

Liquid metal capsules for autonomic thermal energy control.

RSC advances·2026

Related Experiment Video

Updated: Jan 9, 2026

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

996

Label noise learning based SAR target classification method.

Hongqiang Wang1, Yuqing Lan2, Fuzhan Yue3

  • 1School of Software, Beihang University, Beijing, 100191, China; Jiangxi Research Institute, Beihang University, Beijing, 100191, China; State Key Laboratory of Space-Earth Integrated Information Technology, Beijing Institute of Satellite Information Engineering, Beijing, 100095, China.

Neural Networks : the Official Journal of the International Neural Network Society
|December 5, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel method to improve Synthetic Aperture Radar (SAR) target recognition by reducing noise in both features and labels. The approach enhances Convolutional Neural Network (CNN) performance, even with significant data inaccuracies.

Keywords:
Label noise learningSAR image recognitionScattering feature extractionSynthetic aperture radar

More Related Videos

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

5.2K
P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
06:09

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

902

Related Experiment Videos

Last Updated: Jan 9, 2026

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

996
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

5.2K
P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
06:09

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

902

Area of Science:

  • Computer Science
  • Remote Sensing
  • Signal Processing

Background:

  • Synthetic Aperture Radar (SAR) target recognition is vital for image interpretation.
  • Convolutional Neural Networks (CNNs) excel at SAR image classification but require large labeled datasets.
  • SAR data is prone to feature and label noise, degrading CNN performance.

Purpose of the Study:

  • To develop a robust method for SAR target classification that mitigates feature and label noise.
  • To enhance the performance of CNN-based classifiers in the presence of data inaccuracies.

Main Methods:

  • A dynamic L_p-norm regularization-based scattering feature extraction method is proposed to address feature noise.
  • A robust representation learning framework is developed to enhance model robustness against label noise.
  • Neural networks are used to adapt regularization parameters and minimize distances between samples and class prototypes.

Main Results:

  • The proposed method demonstrates robust classification accuracy on MSTAR, SAR-ACD, and FUSAR datasets.
  • Consistent performance is achieved across label noise levels ranging from 0% to 60%.
  • Significant mitigation of adverse effects from annotation inaccuracies is observed.

Conclusions:

  • The developed approach effectively addresses feature and label noise in SAR target classification.
  • This method offers a significant improvement in CNN-based SAR image interpretation, especially with noisy data.
  • The findings contribute to more reliable SAR target recognition systems.