S4Sleep:阐明基于深度学习的睡眠阶段分类模型的设计空间
Tiezhi Wang1, Nils Strodthoff1
1Carl von Ossietzky Universität Oldenburg, Ammerlaender Heerstr. 114-118, Oldenburg, 26129, Lower Saxony, Germany.
Computers in biology and medicine
|February 4, 2025
概括
新的机器学习模型,S4Sleep (spec) 和S4Sleep (ts),显著改善了自动睡眠阶段评分从多睡眠学数据. 这些编码器-预测器架构在没有超参数调整的情况下,在主要数据集上优于现有的方法.
科学领域:
- 人工智能的人工智能
- 生物医学工程 生物医学工程
- 睡眠医学 睡眠医学
背景情况:
- 手动的睡眠阶段评分的多睡眠学 (PSG) 是劳动密集型和耗时的.
- 现有的用于自动睡眠评分的机器学习算法缺乏对建筑设计选择的系统探索.
- 需要强大高效的自动化方法来分析睡眠模式.
研究的目的:
- 在自动睡眠阶段评分的编码器-预测器模型中全面调查建筑设计决策.
- 开发和评估利用结构化状态空间模型的新型机器学习架构.
- 在广泛使用的睡眠数据集上建立新的性能基准.
主要方法:
- 对PSG数据的时间序列和谱图表示的编码器-预测器架构的探索.
- 在拟议的架构中整合结构化状态空间模型.
- 在没有超参数优化的情况下对基准数据集进行S4Sleep (spec) 和S4Sleep (ts) 模型的系统评估.
主要成果:
- 拟议的S4Sleep (spec) 和S4Sleep (ts) 模型在多个基准数据集中始终优于所有现有方法.
- 在睡眠EDF,蒙特利尔睡眠研究档案馆和睡眠心脏健康研究数据集上展示了卓越的性能.
- 这些模型在不需要额外的超参数调整的情况下实现了高精度.
结论:
- 该研究为开发用于睡眠分期的先进机器学习模型提供了关键的架构见解.
- 架构搜索的精细方法为未来的时间序列注释研究提供了有价值的工具.
- 开发的S4Sleep模型代表了自动化睡眠分析的重大进步,并且对其他时间序列任务具有更广泛的适用性.
相关概念视频
Stages of Sleep
168
Sleep progresses through distinct stages, each characterized by specific brain wave patterns and physiological responses ranging from wakefulness to stages of non-rapid eye movement, known as non-REM, to rapid eye movement, referred to as REM. Understanding these stages helps in recognizing how sleep supports various bodily and cognitive functions.
Before sleep begins, in wakefulness, the brain exhibits primarily beta waves, which are high in frequency and low in amplitude, indicating alertness...
Before sleep begins, in wakefulness, the brain exhibits primarily beta waves, which are high in frequency and low in amplitude, indicating alertness...
168
Sleep-Wake Cycles
1.2K
Sleep is an essential physiological process vital to maintaining overall well-being. The reticular activating system (RAS), a network of neurons in the brainstem, regulates wakefulness and sleep. While it may seem passive, sleep consists of distinct cycles, each with its unique characteristics and functions. Two key sleep phases are non-rapid eye movement (NREM) and rapid eye movement (REM).
NREM Sleep
NREM sleep comprises four progressive stages that seamlessly merge:
NREM Sleep
NREM sleep comprises four progressive stages that seamlessly merge:
1.2K


