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

Bayesian Conditional GAN for Unsupervised Anomaly Detection in Structural Health Monitoring Time-Series Dataset.

Yohannes L Alemu1, Christian Walther1, Manuel Schneider2

  • 1Institute of Structural Mechanics, Bauhaus University, 99423 Weimar, Germany.

Sensors (Basel, Switzerland)
|July 15, 2026
PubMed
Summary

Related Concept Videos

Structural Classification of Joints01:20

Structural Classification of Joints

Joints, also known as articulations, are classified based on their structural characteristics, i.e., based on whether the articulating surfaces of the adjacent bones are directly connected by fibrous connective tissue or cartilage, or whether the articulating surfaces contact each other within a fluid-filled joint cavity. These differences serve to divide the joints of the body into three structural classifications.
A fibrous joint is where the adjacent bones are united by fibrous connective...

You might also read

Related Articles

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

Sort by
Same author

CANBERRA: A Phase II Randomized Clinical Trial to Test the Therapeutic Potential of Oral Vicasinabin in Diabetic Retinopathy.

Ophthalmology science·2025
Same author

Visual Function Measurements in Eyes With Diabetic Retinopathy: An Expert Opinion on Available Measures.

Ophthalmology science·2024
Same author

A spatial autocorrelation analysis of road traffic crash by severity using Moran's I spatial statistics: A comparative study of Addis Ababa and Berlin cities.

Accident; analysis and prevention·2024
Same author

Reply.

Ophthalmology·2019
Same author

Reply.

Ophthalmology·2019
Same author

Sustained Benefits from Ranibizumab for Central Retinal Vein Occlusion with Macular Edema: 24-Month Results of the CRYSTAL Study.

Ophthalmology. Retina·2019

This study introduces BcDCGAN, a novel AI model for detecting structural damage in railway catenary poles using vibration data. It achieves high accuracy in identifying anomalies without prior fault examples, enhancing infrastructure safety.

Area of Science:

  • Civil Engineering
  • Artificial Intelligence
  • Structural Health Monitoring

Background:

  • Prestressed concrete catenary poles are vital for high-speed railways.
  • Undetected degradation poses risks to safety and service reliability.
  • Detecting rare structural damage without labeled data is a significant challenge.

Purpose of the Study:

  • To develop an unsupervised anomaly detection method for multivariate vibration time series.
  • To introduce the Bayesian conditional deep convolutional generative adversarial network (BcDCGAN) for this purpose.
  • To enable risk-aware monitoring of railway infrastructure.

Main Methods:

  • Utilized BcDCGAN trained exclusively on healthy acceleration signals with wind-speed conditioning.
  • Developed an uncertainty-based anomaly score combining reconstruction quality, adversarial evaluation, and epistemic uncertainty.
Keywords:
Bayesian conditional deep convolutional generative adversarial networkBayesian inferenceconditional GANstructural health monitoringtemporal causal networksuncertainty quantificationunsupervised anomaly detection

Related Experiment Videos

  • Implemented an adaptive, data-driven threshold for practical deployment.

    • Main Results:

    • BcDCGAN achieved high anomaly recall on a real-world dataset with injected damage-like patterns.
    • The model provided interpretable uncertainty signals and clear separation of normal and anomalous data.
    • Demonstrated effective unsupervised anomaly detection in multivariate vibration time series.

    Conclusions:

    • Bayesian conditional GANs are effective for unsupervised anomaly detection in structural health monitoring.
    • BcDCGAN can support risk-aware monitoring of railway infrastructure under varying conditions.
    • The developed method addresses the challenge of detecting rare structural damage without labeled fault data.