Search papers, labs, and topics across Lattice.
This paper introduces LGFNet, a CTC-guided sequence-to-sequence framework designed to enhance single-channel sleep staging by addressing long-range temporal dependencies and ambiguous stage transitions. By employing a Local-Global Fusion encoder and a CTC-Attention joint training paradigm, LGFNet effectively models both fine-grained dynamics and overarching sleep structure, leading to improved accuracy in recognizing stage boundaries. Extensive evaluations across five public benchmarks reveal that LGFNet outperforms existing state-of-the-art methods, particularly excelling in the challenging N1 stage and transition segments.
LGFNet achieves significant accuracy improvements in sleep staging, particularly in challenging transition segments, outperforming existing methods by notable margins.
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.
