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

Brain waves vary between people. An obvious way to improve automatic sleepstaging for longitudinal sleep monitoring is personalization of algorithmsbased on individual characteristics extracted from the first night of data. Asa single night is a very small amount of data to train a sleep staging model,we propose a Kullback-Leibler (KL) divergence regularized transfer learningapproach to address this problem. We employ the pretrained SeqSleepNet (i.e.the subject independent model) as a starting point and finetune it with thesingle-night personalization data to derive the personalized model. This isdone by adding the KL divergence between the output of the subject independentmodel and the output of the personalized model to the loss function duringfinetuning. In effect, KL-divergence regularization prevents the personalizedmodel from overfitting to the single-night data and straying too far away fromthe subject independent model. Experimental results on the Sleep-EDF Expandeddatabase with 75 subjects show that sleep staging personalization with asingle-night data is possible with help of the proposed KL-divergenceregularization. On average, we achieve a personalized sleep staging accuracy of79.6%, a Cohen's kappa of 0.706, a macro F1-score of 73.0%, a sensitivity of71.8%, and a specificity of 94.2%. We find both that the approach is robustagainst overfitting and that it improves the accuracy by 4.5 percentage pointscompared to non-personalization and 2.2 percentage points compared topersonalization without regularization.

Personalized Automatic Sleep Staging with Single-Night Data: a Pilot Study with KL-Divergence Regularization