Search

Research into sleep–wake behaviors relies on scoring sleep states, normally done by manual inspection of electroencephalogram (EEG) and electromyogram (EMG) recordings. This is a highly time-consuming process prone to inter-rater variability. When studying relationships between sleep and motor function, analyzing arousal states under a four-state system of active wake (AW), quiet wake (QW), nonrapid-eye-movement (NREM) sleep, and rapid-eye-movement (REM) sleep provides greater precision in behavioral analysis but is a more complex model for classification than the traditional three-state identification (wake, NREM, and REM sleep) usually used in rodent models. Characteristic features between sleep–wake states provide potential for the use of machine learning to automate classification. Here, we devised SleepEns, which uses a novel ensemble architecture, the time-series ensemble. SleepEns achieved 90% accuracy to the source expert, which was statistically similar to the performance of two other human experts. Considering the capacity for classification disagreements that are still physiologically reasonable, SleepEns had an acceptable performance of 99% accuracy, as determined blindly by the source expert. Classifications given by SleepEns also maintained similar sleep–wake characteristics compared to expert classifications, some of which were essential for sleep–wake identification. Hence, our approach achieves results comparable to human ability in a fraction of the time. This new machine-learning ensemble will significantly impact the ability of sleep researcher to detect and study sleep–wake behaviors in mice and potentially in humans.

Moiré superlattices in atomically thin van der Waals heterostructures hold great promise for extended control of electronic and valleytronic lifetimes, the confinement of excitons in artificial moiré lattices and the formation of exotic quantum phases. Such moiré-induced emergent phenomena are particularly strong for interlayer excitons, where the hole and the electron are localized in different layers of the heterostructure. To exploit the full potential of correlated moiré and exciton physics, a thorough understanding of the ultrafast interlayer exciton formation process and the real-space wavefunction confinement is indispensable. Here we show that femtosecond photoemission momentum microscopy provides quantitative access to these key properties of the moiré interlayer excitons. First, we elucidate that interlayer excitons are dominantly formed through femtosecond exciton–phonon scattering and subsequent interlayer tunnelling at the interlayer-hybridized Σ valleys. Second, we show that interlayer excitons exhibit a momentum fingerprint that is a direct hallmark of the superlattice moiré modification. Third, we reconstruct the wavefunction distribution of the electronic part of the exciton and compare the size with the real-space moiré superlattice. Our work provides direct access to interlayer exciton formation dynamics in space and time and reveals opportunities to study correlated moiré and exciton physics for the future realization of exotic quantum phases of matter.