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

There is abundant medical data on the internet, most of which are unlabeled.Traditional supervised learning algorithms are often limited by the amount oflabeled data, especially in the medical domain, where labeling is costly interms of human processing and specialized experts needed to label them. Theyare also prone to human error and biased as a select few expert annotatorslabel them. These issues are mitigated by Self-supervision, where we generatepseudo-labels from unlabelled data by seeing the data itself. This paperpresents various self-supervision strategies to enhance the performance of atime-series based Diffusion convolution recurrent neural network (DCRNN) model.The learned weights in the self-supervision pretraining phase can betransferred to the supervised training phase to boost the model's predictioncapability. Our techniques are tested on an extension of a DiffusionConvolutional Recurrent Neural network (DCRNN) model, an RNN with graphdiffusion convolutions, which models the spatiotemporal dependencies present inEEG signals. When the learned weights from the pretraining stage aretransferred to a DCRNN model to determine whether an EEG time window has acharacteristic seizure signal associated with it, our method yields an AUROCscore $1.56\%$ than the current state-of-the-art models on the TUH EEG seizurecorpus.

Improving self-supervised pretraining models for epileptic seizure detection from EEG data