Reproduce “Evaluating the Influence of Temporal Context on Automatic Mouse Sleep Staging through the Application of Human Models” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Javier García Ciudad, Morten Mørup, Birgitte Rahbek Kornum, Alexander Neergaard Zahid
The authors adapt human sequence models to stage mouse sleep, assigning each four-second EEG/EMG epoch to wake, non-REM, or REM. They vary the surrounding context and find balanced accuracy rises modestly from 12 to 28 seconds, with stronger gains in REM. On held-out Tidis, L-SeqSleepNet reaches 92.8 ± 0.9%, versus SPINDLE’s 91.8 ± 0.4%; longer context adds limited benefit.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.