RESUMEN
Sleep is essential for physical and mental health. Polysomnography (PSG) procedures are labour-intensive and time-consuming, making diagnosing sleep disorders difficult. Automatic sleep staging using Machine Learning (ML) - based methods has been studied extensively, but frequently provides noisier predictions incompatible with typical manually annotated hypnograms. We propose an energy optimization method to improve the quality of hypnograms generated by automatic sleep staging procedures. The method evaluates the system's total energy based on conditional probabilities for each epoch's stage and employs an energy minimisation procedure. It can be used as a meta-optimisation layer over the sleep stage sequences generated by any classifier that generates prediction probabilities. The method improved the accuracy of state-of-the-art Deep Learning models in the Sleep EDFx dataset by 4.0% and in the DRM-SUB dataset by 2.8%.
RESUMEN
The physical simultaneity between two events can differ from our point of subjective simultaneity (PSS). Studies using simultaneity judgments (SJ) and temporal order judgments (TOJ) tasks have shown that whether two events are reported as simultaneous is highly context-dependent. It has been recently suggested that the interval between the two events in the previous trial can modulate judgments both in SJ and TOJ tasks, an effect named rapid recalibration. In this work, we investigated rapid recalibration in SJ and TOJ tasks and tested whether centering the range of presented intervals on perceived simultaneity modulated this effect. We found a rapid recalibration effect in TOJ, but not in SJ. Moreover, we found that centering the intervals on objective or subjective simultaneity did not change the pattern of results. Interestingly, we also found no correlations between an individual's PSS in TOJ and in SJ tasks, which corroborates other studies in suggesting that these two psychophysical measures may capture different processes.