计算机科学
蒸馏
人工智能
睡眠(系统调用)
基于知识的系统
睡眠阶段
机器学习
专家系统
知识工程
决策支持系统
决策论
人工神经网络
电子邮件
作者
Zhenning Tang,Xiaoyu Chen,Wutong Li,Chen Chen,Wei Chen
标识
DOI:10.1109/jiot.2026.3707389
摘要
Sleep staging classification holds significant clinical importance in the diagnosis of sleep-related disorders. Sequence-to-sequence and sequence-to-epoch models capture long-range temporal dependencies and typically outperform epoch-by-epoch methods, but their reliance on multiepoch electroencephalogram (EEG) inputs leads to higher computational costs and processing latency, hindering their application in real-time wearable systems. To address this issue, we proposesequence-to-epoch knowledge distillation(S2EKD), which transfers temporal knowledge from a high-latency sequence teacher to a single-epoch student, largely preserving accuracy while enabling low-latency, device-friendly inference. The core of our framework is a novel heterogeneous-input knowledge distillation process. A high-performance, sequence-based teacher network processes a full sequence of$T_{\text {epoch}}$inputs, while a lightweight student network is trained using only the corresponding middle epoch,$S_{\text {epoch}}$(or$T_{\text {epoch, middle}}$). By distilling sequence-level context from the teacher, the student makes temporally informed predictions while preserving its single-epoch feature-extraction pathway. This knowledge transfer is enabled by our novel Seq2Epoch Weight (S2EW) module. Guided by S2EW position-aware weights, the student model learns to align its intermediate features with those of the context-rich teacher, ultimately aggregating its own subepoch features to produce a single, contextually aware prediction. We evaluated our method on three public sleep datasets (Sleep-EDF20, MASS-SS3, and ISRUC-S3). The results demonstrate that S2EKD significantly enhances the performance of single-epoch models over existing methods by successfully transferring sequential knowledge. Crucially, our framework reduces model size to just 42.6% of the teacher network while simultaneously improving performance by 2%–3% and eliminating the input latency inherent to sequence-based approaches, clearing a key barrier for real-time deployment. Furthermore, its versatility was confirmed by successfully adapting it to diverse sequence-based teacher models.
科研通智能强力驱动
Strongly Powered by AbleSci AI