用双向Mamba提升脑电睡眠分期准确率，解决计算成本高和类别不平衡问题。
BiT-MamSleep: Bidirectional Temporal Mamba for EEG Sleep Staging
- 结合双方向Mamba机制建模长短时脑电信号依赖关系。
- 在四个公开数据集上平均准确率达89.6%，显著优于现有方法。
- 适合需要高效、精准睡眠分期的医疗与可穿戴设备应用。
本文针对自动睡眠分期面临的高计算成本、双向时间依赖建模不足及类别不平衡问题，提出BiT-MamSleep新架构。该模型融合三分辨率卷积网络（TRCNN）实现多尺度特征高效提取，结合双向Mamba（BiMamba）机制，通过双向处理脑电数据建模短时与长时依赖。同时引入自适应特征重校准（AFR）模块与时间增强块，动态优化特征重要性，在不增加计算量前提下提升分类精度。为增强鲁棒性，采用焦点损失（Focal Loss）与SMOTE技术缓解类别不平衡。在四个公开数据集上的大量实验表明，BiT-MamSleep显著优于当前最优方法，尤其在处理长段脑电信号与类别不平衡场景中表现优异，实现了更准确、可扩展的睡眠分期。
原文摘要 · Abstract (English)
In this paper, we address the challenges in automatic sleep stage classification, particularly the high computational cost, inadequate modeling of bidirectional temporal dependencies, and class imbalance issues faced by Transformer-based models. To address these limitations, we propose BiT-MamSleep, a novel architecture that integrates the Triple-Resolution CNN (TRCNN) for efficient multi-scale feature extraction with the Bidirectional Mamba (BiMamba) mechanism, which models both short- and long-term temporal dependencies through bidirectional processing of EEG data. Additionally, BiT-MamSleep incorporates an Adaptive Feature Recalibration (AFR) module and a temporal enhancement block to dynamically refine feature importance, optimizing classification accuracy without increasing computational complexity. To further improve robustness, we apply optimization techniques such as Focal Loss and SMOTE to mitigate class imbalance. Extensive experiments on four public datasets demonstrate that BiT-MamSleep significantly outperforms state-of-the-art methods, particularly in handling long EEG sequences and addressing class imbalance, leading to more accurate and scalable sleep stage classification.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。