English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The external visual inspections of rolling stock's underfloor equipment arecurrently being performed via human visual inspection. In this study, weattempt to partly automate visual inspection by investigating anomalyinspection algorithms that use image processing technology. As the railroadmaintenance studies tend to have little anomaly data, unsupervised learningmethods are usually preferred for anomaly detection; however, training cost andaccuracy is still a challenge. Additionally, a researcher created anomalousimages from normal images by adding noise, etc., but the anomalous targeted inthis study is the rotation of piping cocks that was difficult to create usingnoise. Therefore, in this study, we propose a new method that uses styleconversion via generative adversarial networks on three-dimensional computergraphics and imitates anomaly images to apply anomaly detection based onsupervised learning. The geometry-consistent style conversion model was used toconvert the image, and because of this the color and texture of the image weresuccessfully made to imitate the real image while maintaining the anomalousshape. Using the generated anomaly images as supervised data, the anomalydetection model can be easily trained without complex adjustments andsuccessfully detects anomalies.

Supervised Anomaly Detection Method Combining Generative Adversarial Networks and Three-Dimensional Data in Vehicle Inspections