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: Sep 18, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.0K

Novel conditional tabular generative adversarial network based image augmentation for railway track fault detection.

Ali Raza1, Rukhshanda Sehar2, Abdul Moiz2

  • 1Department of Software Engineering, University of Lahore, Lahore, Pakistan.

Peerj. Computer Science
|June 26, 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

Measles Epidemiology, Transmission, and Surveillance Characteristics in Ethiopia, 2018-2024.

Journal of epidemiology and global health·2026
Same author

Unmasking Juvenile Systemic Lupus Erythematosus (JSLE): Multisystemic Manifestations in an Adolescent Male, A Rare Case Report.

Clinical case reports·2026
Same author

Robotic assisted versus non-robotic retroperitoneal lymph node dissection for testicular cancer: an updated systematic review and meta-analysis.

Journal of robotic surgery·2026
Same author

Detection of monkeypox skin lesions using edge enhancement algorithms integrated with hybrid deep learning.

Digital health·2026
Same author

The impact of acute normovolemic hemodilution on blood transfusions in cardiac surgery: a GRADE-assessed systematic review and meta-analysis of 30 randomized controlled trials with trial sequential analysis.

Naunyn-Schmiedeberg's archives of pharmacology·2026
Same author

Infective Endocarditis With Coronary Artery Embolization and Multisystem Involvement in a Patient With a History of IV Drug Use: A Case Report.

Journal of community hospital internal medicine perspectives·2026

This study introduces an advanced generative neural network for railway track fault detection. A novel conditional tabular generative adversarial network (CTGAN) approach improved accuracy, enhancing rail safety and reducing maintenance costs.

Area of Science:

  • Engineering
  • Artificial Intelligence
  • Computer Science

Background:

  • Traditional railway track fault detection methods (manual inspection, basic sensors) are costly, error-prone, and lack real-time monitoring.
  • These limitations lead to safety risks and operational inefficiencies in rail transport.
  • Artificial intelligence (AI)-based image classification offers a promising solution for enhanced fault detection.

Purpose of the Study:

  • To develop an advanced generative neural network for efficient railway track fault detection.
  • To improve the accuracy, efficiency, and reliability of identifying defects like cracks, misalignments, and wear.

Main Methods:

  • Proposed a novel conditional tabular generative adversarial network (CTGAN)-based image augmentation technique to generate synthetic railway track images.
Keywords:
Deep learningFault detectionGANGenerative AIMachine learningRailway track fault

More Related Videos

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

650

Related Experiment Videos

Last Updated: Sep 18, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.0K
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

650
  • Developed and compared five advanced neural network techniques for railway track image classification.
  • Applied hyperparameter optimization and k-fold cross-validation for robust performance evaluation.

    • Main Results:

    • The random forest approach achieved a high accuracy score of 0.99 in railway track fault detection, surpassing state-of-the-art methods.
    • The CTGAN-based data augmentation effectively produced realistic synthetic image data.
    • Optimized hyperparameters and cross-validation confirmed the model's robust performance.

    Conclusions:

    • The developed AI approach significantly enhances railway track fault detection accuracy and reliability.
    • Implementation leads to improved operational efficiency and reduced maintenance costs.
    • The research contributes to a substantial improvement in the overall safety and dependability of rail transportation.