发表机构
NIMISHES Lab; Canadian University of Bangladesh（NIMISHES实验室; 孟加拉国加拿大大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出SleepEffFormer TAS，结合CNN与Transformer及非参数转换感知平滑，在单通道脑电睡眠分期中达到83.9%准确率，参数少3-5倍，并提升少数类性能。
AI 中文摘要
基于单通道脑电的自动睡眠分期是走出多导睡眠监测实验室、实现大规模睡眠监测的一条有前景的途径。本文提出SleepEffFormer TAS，一个高效且可解释的系统，由四步长块一维CNN特征提取器、两层预归一化Transformer编码器以及一个非参数的转换感知平滑（TAS）层组成，该层可抑制预测分期之间生理上不现实的转换。在Sleep-EDF Expanded数据集上，使用来自Fpz-Cz通道的78个整夜脑电记录，采用受试者独立留出划分进行测试，所提模型达到了83.9%的准确率、78.9%的宏F1分数和0.765的Cohen's kappa，可学习参数约367K。该性能与AttnSleep相当，而参数数量减少3至5倍。消融研究表明，与基于CNN的系统相比，Transformer编码器将宏F1提高了6.6个百分点，而TAS层在不引入任何可训练参数的情况下额外提供了1.8个百分点的提升。加权损失对于改善少数N1睡眠阶段的分类也至关重要。所提模型生成的注意力图揭示了生理上合理的睡眠阶段相关脑电特征。
英文摘要
Automated sleep stage classification based on single-channel EEG is a promising pathway to large-scale sleep monitoring outside the polysomnographic lab. This paper proposes SleepEffFormer TAS, an efficient and interpretable system that consists of a four-stride-block 1D CNN feature extractor, a two-layer pre-normalization Transformer encoder, and a non-parametric Transition-Aware Smoothing (TAS) layer that suppresses physiologically unrealistic transitions between predicted stages. When tested on the Sleep-EDF Expanded dataset using 78 all-night EEG recordings from the Fpz-Cz channel with a subject-wise held-out split, the proposed model achieves 83.9% accuracy, a 78.9% macro F1-score, and a Cohen's kappa of 0.765 with approximately 367K learnable parameters. This performance is comparable to AttnSleep while using 3-5 times fewer parameters. Ablation studies show that the Transformer encoder improves macro F1 by 6.6 percentage points over a CNN-based system, while the TAS layer provides an additional 1.8 percentage point improvement without introducing any trainable parameters. Weighted loss is also critical for improving classification of the minority N1 sleep stage. Attention maps generated by the proposed model reveal physiologically sensible sleep-stage-related EEG features.
