Sleep Staging Framework with Physiologically Harmonized Sub-Networks

•This paper proposes a reasonable sleep stage scoring framework, where we take into account the physiological characteristics of brain waves.•A novel sleep data processing is proposed to automate the sleep scoring task. By wrapping up the sub-networks that are responsible for learning the transient and overall characteristics of EEG during sleep with Transformer, a parallel model for sequence, the performance is improved when compared against the baseline models.•Considering the practicality in a real clinical setting, this paper adopts a mixed-precision strategy to speed up and alleviate the resource cost.