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 Videos

DeepTrackSecure: an integrated classification-detection system with predictive risk analytics for proactive railway

P Balakrishnan1, A Anny Leema1, S Suresh Nagarajan1

  • 1School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India.

Frontiers in Artificial Intelligence
|June 1, 2026
PubMed
Summary
This summary is machine-generated.

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

EPIC-NET: EEG-based epilepsy classification and brain localization using Optuna wave-gated recurrent unit network.

Frontiers in computational neuroscience·2026
Same author

Comparative Studies of the Photoluminescence Properties of the Metal Ions Co-doped with the Rare Earth Ions (Bi<sup>3+</sup>, Eu<sup>3+</sup>; Bi<sup>3+</sup>, Tb<sup>3+</sup>; Bi<sup>3+</sup>, Tb<sup>3+</sup>, Eu<sup>3+</sup> and Pb<sup>2+</sup>, Eu<sup>3+</sup>) in the Silicate Based Single Phosphors for White Light Emitting Diode Applications.

Journal of fluorescence·2026
Same author

Evaluation of submandibular gland involvement in oral squamous cell carcinoma patients.

International journal of oral and maxillofacial surgery·2025
Same author

Data-driven pit stop decision support for Formula 1 using deep learning models.

Frontiers in artificial intelligence·2025
Same author

HairSentinel: a time-aware anomaly detection framework for forecasting hairfall trends using temporal fusion transformers.

Frontiers in artificial intelligence·2025
Same author

Gene-LLMs: a comprehensive survey of transformer-based genomic language models for regulatory and clinical genomics.

Frontiers in genetics·2025

DeepTrackSecure uses deep learning for railway track fault detection and risk prediction. This AI system enhances safety by prioritizing maintenance needs based on defect severity.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Railway Engineering

Background:

  • Railway track failures present significant safety risks, necessitating efficient detection and prioritization.
  • Manual inspection methods are labor-intensive, error-prone, and inadequate for large-scale monitoring.
  • Existing methods lack quantitative severity assessment for informed risk management.

Purpose of the Study:

  • To introduce DeepTrackSecure, a deep learning framework for automated railway track fault detection.
  • To develop a severity-aware risk prediction model for prioritizing maintenance.
  • To evaluate the system's performance, robustness, and suitability for deployment.

Main Methods:

  • A multi-stage deep learning approach utilizing ResNet50 for initial image screening and YOLOv5 for precise fault localization.
Keywords:
ResNet50ablation studydeep learningedge and cloud deploymentimage classificationobject detectionrailway track fault detectionrandom forest

Related Experiment Videos

  • Development of a quantitative severity score based on defect area, detection confidence, and frequency.
  • Classification of track conditions into risk levels (low, medium, high) using Random Forest and XGBoost models.

    • Main Results:

    • DeepTrackSecure accurately detects and localizes railway track defects, providing a severity score.
    • The system effectively classifies track conditions into risk categories, validated by expert opinion.
    • Ablation studies confirmed the contribution of each component, and performance analysis indicated suitability for edge/cloud deployment.

    Conclusions:

    • DeepTrackSecure serves as a valuable decision-support tool for railway maintenance scheduling.
    • The AI framework enhances safety by enabling proactive and prioritized maintenance interventions.
    • Further validation and recall improvement are recommended before operational deployment.