用事件驱动方法让单通道脑电在边缘设备高效睡眠分期。
NeuroSleep: Neuromorphic Event-Driven Single-Channel EEG Sleep Staging for Edge-Efficient Sensing
- 将脑电信号转为分层事件流，前端实现精度与稀疏性的可控平衡。
- 仅用0.932百万参数即达74.2%准确率，计算量比密集处理降低53.6%。
- 适合可穿戴设备部署，显著提升睡眠监测的能效与实用性。
目标：可穿戴边缘平台上的可靠、连续神经传感是长期健康监测的基础；然而，基于脑电图（EEG）的睡眠监测常因高频率密集计算，在严苛能耗预算下难以实现。方法：本文提出NeuroSleep，一种集成事件驱动感知与推理的节能睡眠分期系统。NeuroSleep首先利用残差自适应多尺度增量调制（R-AMSDM）将原始EEG转换为互补的多尺度双极事件流，实现感知前端的显式保真度-稀疏性权衡。此外，系统采用分层推理架构，包括用于局部特征提取的事件自适应多尺度响应（EAMR）模块、用于上下文聚合的局部时序注意力（LTAM）模块，以及用于捕捉长期状态持续性的段落漏失积分-放电（ELIF）模块。主要结果：在包含单通道EEG的Sleep-EDF Expanded睡眠数据集（SC子集）上，通过受试者独立的五折交叉验证，NeuroSleep实现了74.2%的平均准确率，参数量仅为0.932百万，相比密集处理降低了约53.6%的稀疏性调整后有效运算量。相较于代表性密集型Transformer基线，其准确率提升7.5%，计算负载减少45.8%。意义：通过结合类脑事件编码与状态感知上下文建模，NeuroSleep为单通道睡眠分期提供了面向部署的框架，减少了冗余高频处理，提升了可穿戴和边缘平台的能量可扩展性。
原文摘要 · Abstract (English)
Objective. Reliable, continuous neural sensing on wearable edge platforms is fundamental to long-term health monitoring; however, for electroencephalography (EEG)-based sleep monitoring, dense high-frequency processing is often computationally prohibitive under tight energy budgets. Approach. To address this bottleneck, this paper proposes NeuroSleep, an integrated event-driven sensing and inference system for energy-efficient sleep staging. NeuroSleep first converts raw EEG into complementary multi-scale bipolar event streams using Residual Adaptive Multi-Scale Delta Modulation (R-AMSDM), enabling an explicit fidelity-sparsity trade-off at the sensing front end. Furthermore, NeuroSleep adopts a hierarchical inference architecture that comprises an Event-based Adaptive Multi-scale Response (EAMR) module for local feature extraction, a Local Temporal-Attention Module (LTAM) for context aggregation, and an Epoch-Leaky Integrate-and-Fire (ELIF) module to capture long-term state persistence. Main results. Experimental results using subject-independent 5-fold cross-validation on the Sleep-EDF Expanded sleep-cassette (SC) subset with single-channel EEG demonstrate that NeuroSleep achieves a mean accuracy of 74.2% with only 0.932 M parameters while reducing sparsity-adjusted effective operations by approximately 53.6% relative to dense processing. Compared to the representative dense Transformer baseline, NeuroSleep improves accuracy by 7.5% with a 45.8% reduction in computational load. Significance. By coupling neuromorphic event encoding with state-aware context modeling, NeuroSleep offers a deployment-oriented framework for single-channel sleep staging that reduces redundant high-rate processing and improves energy scalability for wearable and edge platforms.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。