发表机构
School of Mathematics and Systems Science, Shandong University of Science and Technology; School of Artificial Intelligence, Shandong Women’s University; School of Computer Science and Engineering, South China University of Technology（山东科技大学数学与系统科学学院; 山东女子学院人工智能学院; 华南理工大学计算机科学与工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对睡眠分期难题，提出LGFNet框架，通过局部-全局融合编码器及CTC-注意力联合训练等方法，有效建模时间动态与睡眠结构，统一时间对齐与上下文建模，经三阶段解码策略提升性能，在跨数据集评估中优于现有单通道方法。
AI 中文摘要
睡眠分期因长期时间依赖性、阶段转换模糊（尤其是N1阶段）以及不同受试者、采样率和脑电图采集方式之间的显著分布变化而具有挑战性。在可穿戴和实际应用所需的单通道、低延迟场景中，这些困难进一步加剧。为解决这些问题，我们提出了LGFNet，一种用于稳健睡眠分期的基于CTC引导的序列到序列框架。LGFNet引入了局部-全局融合编码器，联合建模细粒度时间动态和长期睡眠结构，克服了传统串行混合架构的局限性。采用CTC-注意力联合训练范式，将时间对齐与上下文相关建模统一起来，能够更准确地识别阶段边界和转换。此外，设计了一种三阶段解码策略，利用CTC引导解码和基于维特比的平滑来减少误差积累并增强生理一致性。在五个公共基准上的广泛跨数据集评估表明，LGFNet始终优于现有单通道方法。特别是在Sleep-EDF-78上，LGFNet在准确率、宏F1和kappa方面分别比DMIN高出1.27%、1.74%和1.93%，在N1和转换段有显著提升，突出了其在不同采样率、采集方式和记录环境下的稳健性和强大泛化能力。
英文摘要
Sleep staging remains challenging due to long-range temporal dependencies, ambiguous stage transitions-particularly in N1-and substantial distribution shifts across subjects, sampling rates, and EEG montages. These difficulties are further amplified in single-channel, low-latency scenarios required by wearable and real-world applications. To address these issues, we propose LGFNet, a CTC-guided sequence-to-sequence framework for robust sleep staging. LGFNet introduces a Local-Global Fusion encoder that jointly models fine-grained temporal dynamics and long-range sleep structure, overcoming the limitations of conventional serial hybrid architectures. A CTC-Attention joint training paradigm is adopted to unify temporal alignment with context-dependent modeling, enabling more accurate recognition of stage boundaries and transitions. Furthermore, a three-stage decoding strategy is devised, leveraging CTC-guided decoding and Viterbi-based smoothing to reduce error accumulation and enforce physiological consistency. Extensive cross-dataset evaluations on five public benchmarks demonstrate that LGFNet consistently outperforms state-of-the-art single-channel methods. In particular, on Sleep-EDF-78, LGFNet surpasses DMIN by +1.27% accuracy, +1.74% macro-F1, and +1.93% kappa, with pronounced gains on N1 and transition segments, highlighting its robustness and strong generalization across diverse sampling rates, montages, and recording environments.
