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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In the data obtained by laser interferometric gravitational wave detectors,transient noise with non-stationary and non-Gaussian features occurs at a highrate. This often results in problems such as detector instability and thehiding and/or imitation of gravitational-wave signals. This transient noise hasvarious characteristics in the time--frequency representation, which isconsidered to be associated with environmental and instrumental origins.Classification of transient noise can offer clues for exploring its origin andimproving the performance of the detector. One approach for accomplishing thisis supervised learning. However, in general, supervised learning requiresannotation of the training data, and there are issues with ensuring objectivityin the classification and its corresponding new classes. By contrast,unsupervised learning can reduce the annotation work for the training data andensure objectivity in the classification and its corresponding new classes. Inthis study, we propose an unsupervised learning architecture for theclassification of transient noise that combines a variational autoencoder andinvariant information clustering. To evaluate the effectiveness of the proposedarchitecture, we used the dataset (time--frequency two-dimensional spectrogramimages and labels) of the Laser Interferometer Gravitational-wave Observatory(LIGO) first observation run prepared by the Gravity Spy project. The classesprovided by our proposed unsupervised learning architecture were consistentwith the labels annotated by the Gravity Spy project, which manifests thepotential for the existence of unrevealed classes.

Unsupervised Learning Architecture for Classifying the Transient Noise of Interferometric Gravitational-wave Detectors