PicoSleepNet:使用单通道EEG信号的尖端神经网络进行超轻量级睡眠阶段分类
IEEE journal of biomedical and health informatics
|August 25, 2025
概括
这项研究介绍了PicoSleepNet, 一种使用尖端神经网络和单通道EEG的超轻量级睡眠分期系统. 它大大减少了可穿戴健康监测的数据和计算.
科学领域:
- 生物医学工程
- 计算神经科学
- 信号处理
背景情况:
- 传统的使用脑电图 (EEG) 信号的睡眠阶段分类方法是计算密集和耗电的,限制了它们在可穿戴设备中的使用.
- 现有的方法通常依赖于多位尼奎斯特采样和密集的计算架构,导致高复杂性和功耗.
- 需要超轻,高效的睡眠阶段解决方案,用于边缘设备的实时监控.
研究的目的:
- 推出PicoSleepNet,一种创新的超轻量级睡眠阶段分类方法.
- 在资源有限的可穿戴设备和神经形态硬件上部署睡眠分阶段系统.
- 在保持高精度的同时,减少睡眠阶段分类的计算复杂性和功耗.
主要方法:
- 使用单通道脑电图 (EEG) 信号与尖端神经网络 (SNN).
- 实现单位子尼奎斯特交叉采样 (LCS) 适应性数据编码,减少数据体积6.98×.
- 采用稀疏循环尖端神经网络 (RSNN),并通过掩盖反向传播和稀疏规则化 (MaskedBPSR) 和量子化意识培训 (QAT) 进行优化.
主要成果:
- 在公开数据集 (SleepEDF-20,Sleep-EDF-78,ISRUC-Sleep) 上,PicoSleepNet获得了竞争力的准确度 (83.5%,77.9%,79.4%) 和宏观F1得分 (75.2%,68.1%和77.2%).
- 该模型是超轻的,具有14.0-25.8K参数 (近2×减小) 和681.4-842.0K操作 (27×减小).
- 实现了显著的1480×计算功耗降低,证明了硬件友好的部署能力.
结论:
- 在可穿戴设备和神经形态硬件上实现超轻量级睡眠阶段的可行解决方案.
- 使用LCS,稀疏RSNN,MaskedBPSR和QAT的组合可显著降低计算负载和功耗.
- 这种方法为实时,持续的健康监测通过高级睡眠分析的更广泛应用铺平了道路.
更多相关视频
10:45Simultaneous Electroencephalography, Real-time Measurement of Lactate Concentration and Optogenetic Manipulation of Neuronal Activity in the Rodent Cerebral Cortex
Published on: December 19, 2012
20.4K
10:56Quantifying Infra-slow Dynamics of Spectral Power and Heart Rate in Sleeping Mice
Published on: August 2, 2017
10.1K
相关概念视频
Stages of Sleep
455
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...
455
Understanding Sleep
503
Sleep, an essential biological state, involves significant reductions in physical activity, sensory awareness, and interaction with the environment. This complex physiological process is primarily regulated by specific brain regions, notably the hypothalamus and pons, which govern the sleep-wake cycle or circadian rhythm.
The circadian rhythm, a nearly 24-hour cycle, is deeply influenced by environmental light cues. Light exposure directly affects the hypothalamus, which in turn regulates...
The circadian rhythm, a nearly 24-hour cycle, is deeply influenced by environmental light cues. Light exposure directly affects the hypothalamus, which in turn regulates...
503
