发表机构
Center for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, CAS; Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China; Technical University of Munich（中国科学院香港创新研究院人工智能与机器人中心; 电子科技大学深圳高等研究院; 慕尼黑工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SemPSG是一种语义通道感知基础模型，显式建模通道身份的生理语义，通过语义条件时间序列编码器和多视图图像编码器，在睡眠分期等多项任务上优于通用及PSG专用基础模型，并跨异构配置泛化。
AI 中文摘要
多导睡眠图（PSG）整合多种生理信号以全面表征人类睡眠，然而各中心之间异构的通道配置对可迁移的表示学习构成了重大挑战。现有基础模型主要关注生理建模或时间学习，而通道身份通常被视为固定的结构索引，忽略了由信号模态和参考配置所编码的生理语义。为此，我们提出SemPSG，一种用于异构PSG分析的语义通道感知基础模型。SemPSG显式地表示通道身份的生理语义，并将其纳入信号表示学习和通道聚合中，从而实现对多样化数据配置的灵活建模。具体而言，一个语义条件时间序列编码器捕获信号特定的时间动态和跨信号交互，而一个多视图图像编码器则从相同的生理记录中提取互补的时频和形态模式。我们在睡眠及健康相关任务上评估SemPSG，包括睡眠分期、睡眠障碍呼吸分析、疾病预测、认知与情绪识别以及人口统计学估计。大量实验表明，与通用时间序列基础模型和PSG专用基础模型相比，SemPSG均取得了一致的性能提升，并在跨异构数据集和多样化通道配置中展现出良好的泛化能力。
英文摘要
Polysomnography (PSG) integrates multiple physiological signals to provide a comprehensive characterization of human sleep, yet its heterogeneous channel configurations across centers pose substantial challenges for transferable representation learning. Existing foundation models mainly focus on physiological modeling or temporal learning, while channel identity is often treated as a fixed structural index, overlooking the physiological semantics encoded by signal modality and reference configuration. To this end, we propose SemPSG, a Semantic channel-aware foundation model for heterogeneous PSG analysis. SemPSG explicitly represents the physiological semantics of channel identity and incorporates them into both signal representation learning and channel aggregation, enabling flexible modeling across diverse data configurations. Specifically, a semantic-conditioned time-series encoder captures signal-specific temporal dynamics and cross-signal interactions, while a multi-view image encoder extracts complementary time-frequency and morphological patterns from the same physiological recordings. We evaluate SemPSG on sleep and health-related tasks, including sleep staging, sleep-disorder breathing analysis, disease prediction, cognition and emotion recognition, and demographic estimation. Extensive experiments demonstrate consistent improvements over both general-purpose time series foundation models and PSG-specific foundation models, together with generalization across heterogeneous datasets across diverse channel configurations.
