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

Self-supervised learning addresses the challenge encountered by manysupervised methods, i.e. the requirement of large amounts of annotated data.This challenge is particularly pronounced in fields such as theelectroencephalography (EEG) research domain. Self-supervised learning operatesinstead by utilizing pseudo-labels, which are generated by pretext tasks, toobtain a rich and meaningful data representation. In this study, we aim atintroducing a dual-stream pretext task architecture that operates both in thetime and frequency domains. In particular, we have examined the incorporationof the novel Frequency Similarity (FS) pretext task into two existing pretexttasks, Relative Positioning (RP) and Temporal Shuffling (TS). We assess theaccuracy of these models using the Physionet Challenge 2018 (PC18) dataset inthe context of the downstream task sleep stage classification. The inclusion ofFS resulted in a notable improvement in downstream task accuracy, with a 1.28percent improvement on RP and a 2.02 percent improvement on TS. Furthermore,when visualizing the learned embeddings using Uniform Manifold Approximationand Projection (UMAP), distinct clusters emerge, indicating that the learnedrepresentations carry meaningful information.

A novel dual-stream time-frequency contrastive pretext tasks framework for sleep stage classification