莫菲斯网:嵌入式在线系统的资源高效睡眠阶段分类器
Ali Kavoosi1, Morgan P Mitchell2, Raveen Kariyawasam3
1MRC Brain Network Dynamics Unit, University of Oxford, Oxford, UK.
Conference proceedings. IEEE International Conference on Systems, Man, and Cybernetics
|February 22, 2024
概括
本研究提出了一个紧的,节能的深度学习模型,用于微控制器上的实时睡眠阶段分类 (SSC). 优化的算法可以在设备上进行睡眠分析,用于可扩展的治疗应用.
科学领域:
- 生物医学工程 生物医学工程
- 人工智能的人工智能
- 睡眠医学 睡眠医学
背景情况:
- 手动睡眠阶段分类 (SSC) 耗时且限制了治疗应用.
- 对于SSC存在深度学习模型,但需要大量的计算资源,阻碍实时和边缘部署.
- 可穿戴设备为可扩展的基于睡眠的疗法提供了潜力,如果SSC可以有效地自动化.
研究的目的:
- 开发一个紧的,节能的深度学习模型,用于实时,在设备上的睡眠阶段分类.
- 为了使基于睡眠的疗法能够在具有硬件限制的嵌入式系统上部署.
- 为了减少SSC模型的计算复杂性,而不会影响准确性.
主要方法:
- 开发了一种新的,紧的深度学习架构,用于睡眠阶段分类.
- 使用8位量化优化模型以减少内存足迹和提高功率效率.
- 在三个公共睡眠数据集上测试了该模型,并将其实现在一个Arm Cortex-M4处理器上.
主要成果:
- 紧型号的性能与最先进的方法相美.
- 与现有方法相比,模型复杂性减少了多达280倍.
- 量子化模型仅显示0.95%的平均精度下降,并且在Arm Cortex-M4上实现了1.6秒的延迟,用于在线SSC.
结论:
- 开发的紧型深度学习模型可以实现高效的实时设备睡眠阶段分类.
- 这种方法有助于将睡眠分析集成到可穿戴设备中,以进行可扩展的治疗干预.
- 节能和低复杂度的设计允许在微控制器上部署,克服了以前的限制.
相关概念视频
01:22Stages of Sleep
192
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...
192
01:24Sleep-Wake Cycles
1.3K
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:
1.3K