This paper proposes a novel framework for automatically capturing the
time-frequency nature of electroencephalogram (EEG) signals of human sleep
based on the authoritative sleep medicine guidance. The framework consists of
two parts: the first part extracts informative features by partitioning the
input EEG spectrograms into a sequence of time-frequency patches. The second
part is constituted by an attention-based architecture to efficiently search
for the correlation between partitioned time-frequency patches and defining
factors of sleep stages in parallel. The proposed pipeline is validated on the
Sleep Heart Health Study dataset with new state-of-the-art results for the
stages wake, N2, and N3, obtaining respective F1 scores of 0.93, 0.88, and
0.87, with only EEG signals used. The proposed method also has a high
inter-rater reliability of 0.80 kappa. We also visualize the correspondence
between sleep staging decisions and features extracted by the proposed method,
providing strong interpretability for our model.

本文提出了一种新的框架，可以自动捕捉到基于权威睡眠医学指导的人类睡眠的脑电图信号的时频特性，并通过使用时间 - 频率补丁序列划分输入的 EEG 频谱图的信息特征和基于注意力的架构并行地有效地搜索划分的时频补丁与睡眠阶段的定义因素之间的相关性来对其进行定义。提出的方法在只使用脑电图信号的情况下，在 Sleep Heart Health Study 数据集上得出了新的最先进结果，分别获得了 0.93、0.88 和 0.87 的 F1 得分，并且具有高达 0.80 kappa 的高度一致性。我们还可视化了睡眠分期决策和所提出方法提取的特征之间的对应关系，为我们的模型提供了强大的可解释性。