S2EKD: Sequence-to-Epoch Knowledge Distillation for Real-Time Sleep Staging

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
出处
期刊:IEEE Internet of Things Journal [Institute of Electrical and Electronics Engineers]
卷期号:13 (17): 39503-39517
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.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
nature发布了新的文献求助10
1秒前
xfy发布了新的文献求助200
2秒前
3秒前
慕遥的应助被净心采纳,获得10
3秒前
丘比特的应助被失眠孤兰采纳,获得10
3秒前
英姑的应助被失眠孤兰采纳,获得10
3秒前
4秒前
含蓄雨柏完成签到,获得积分10
4秒前
Nole的应助被严肃的梨采纳,获得10
4秒前
鸡血红发布了新的文献求助10
5秒前
6秒前
7秒前
海盗船长发布了新的文献求助10
7秒前
8秒前
幽默山槐完成签到,获得积分10
8秒前
8秒前
从容雅柏完成签到,获得积分10
8秒前
张顺完成签到,获得积分10
8秒前
不想科研的科研人完成签到,获得积分10
8秒前
9秒前
Sereilla完成签到,获得积分10
9秒前
Cherry完成签到 ,获得积分10
10秒前
lynyee关注了科研通微信公众号
10秒前
11秒前
123发布了新的文献求助10
11秒前
11秒前
爆米花的应助被无限之双采纳,获得10
11秒前
12秒前
12秒前
三斤鱼完成签到,获得积分10
12秒前
12秒前
不安晓曼发布了新的文献求助10
13秒前
13秒前
李之恒完成签到,获得积分10
14秒前
14秒前
15秒前
function发布了新的文献求助10
15秒前
15秒前
July0717_发布了新的文献求助10
16秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Handbook of Sport Coaching Research 1000
Orthognathic Surgery - 2 Volume Set 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8193425
求助须知:如何正确求助?哪些是违规求助? 9579620
关于积分的说明 21866505
捐赠科研通 7793025
什么是DOI,文献DOI怎么找? 3437297
关于科研通互助平台的介绍 2560718
邀请新用户注册赠送积分活动 2484128