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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Sleep stage classification constitutes an important preliminary exam in thediagnosis of sleep disorders. It is traditionally performed by a sleep expertwho assigns to each 30s of signal a sleep stage, based on the visual inspectionof signals such as electroencephalograms (EEG), electrooculograms (EOG),electrocardiograms (ECG) and electromyograms (EMG). We introduce here the firstdeep learning approach for sleep stage classification that learns end-to-endwithout computing spectrograms or extracting hand-crafted features, thatexploits all multivariate and multimodal Polysomnography (PSG) signals (EEG,EMG and EOG), and that can exploit the temporal context of each 30s window ofdata. For each modality the first layer learns linear spatial filters thatexploit the array of sensors to increase the signal-to-noise ratio, and thelast layer feeds the learnt representation to a softmax classifier. Our modelis compared to alternative automatic approaches based on convolutional networksor decisions trees. Results obtained on 61 publicly available PSG records withup to 20 EEG channels demonstrate that our network architecture yieldsstate-of-the-art performance. Our study reveals a number of insights on thespatio-temporal distribution of the signal of interest: a good trade-off foroptimal classification performance measured with balanced accuracy is to use 6EEG with 2 EOG (left and right) and 3 EMG chin channels. Also exploiting oneminute of data before and after each data segment offers the strongestimprovement when a limited number of channels is available. As sleep experts,our system exploits the multivariate and multimodal nature of PSG signals inorder to deliver state-of-the-art classification performance with a smallcomputational cost.

A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series