AI summaryⓘ
The authors created a new method called SwinSleepNet to improve automatic sleep stage detection, especially for tricky stages where sleep changes or is unclear. Their approach looks at brainwave signals in two ways—both the original electrical signals and their time-frequency patterns—using special tools to capture detailed features inside each sleep segment. They also consider the order of sleep stages over time to better understand transitions. Tests on multiple sleep datasets showed their method works well overall and is particularly good at recognizing hard-to-detect sleep stages like N1. This shows that carefully analyzing detailed and combined brainwave information can help sleep monitoring.
sleep stagingEEGtime-frequency transformationSwin Transformerconvolutional encoderintra-epoch featuresinter-epoch contextN1 sleep stageSleep-EDF datasetautomatic sleep analysis
Abstract
Automatic sleep staging is a critical role in sleep disorder diagnosis, sleep quality assessment, and long-term health monitoring; however, existing approaches suffer poor performance on ambiguous and transition-related sleep stages, caused by inadequate modeling of fine-grained intra-epoch structures and complex cross-region spectral dependencies. Traditional epoch-level encoders commonly fail to extract subtle temporal microstructures and intra-epoch cross-region interactions, resulting in unsatisfactory recognition accuracy for hard categories such as the N1 stage. To tackle these drawbacks, we propose SwinSleepNet, a hierarchical context-aware dual-stream framework that separately optimizes intra-epoch representation learning and inter-epoch contextual modeling. Concretely, we characterize each sleep epoch from two complementary perspectives: raw time-domain EEG signal and its time-frequency transformation. The time-domain branch adopts convolutional encoders to capture fine waveform temporal details, and the time-frequency branch uses Swin Transformer to extract local spectro-temporal features, hierarchical multi-scale information and long-range spatial dependencies. The multi-branch extracted features are fused into integrated embeddings, which are optimized by a bidirectional context module to capture cross-epoch temporal dependencies for final sleep stage classification. Comprehensive experiments on Sleep-EDF-20, Sleep-EDF-78 and SHHS datasets verify that our method achieves competitive overall performance, and exhibits stronger robustness and stability on difficult N1 stages and transitional epochs. The results prove that optimized intra-epoch representation learning based on hierarchical architecture greatly benefits automatic sleep staging tasks.