自动化优化神经网络，让可穿戴设备低功耗精准测血压
End-to-end Automated Deep Neural Network Optimization for PPG-based Blood Pressure Estimation on Wearables
- 用硬件感知的自动设计流程优化模型结构、剪枝和精度
- 参数减少7.5倍，误差降低7.99%，内存仅需512kB
- 适合在低功耗芯片上实现全自动血压监测
基于光电容积脉搏波（PPG）的血压（BP）估算是一个挑战性任务，尤其在资源受限的可穿戴设备上。尽管深度神经网络（DNNs）通过重构血压波形或直接回归血压值已实现高精度，但其高内存、计算与能耗需求阻碍了部署。本文提出一种完全自动化的端到端DNN设计流程，结合硬件感知神经架构搜索（NAS）、剪枝和混合精度搜索（MPS），生成适用于超低功耗多核片上系统（SoC）的紧凑血压预测模型。基于四个公开数据集的基准模型，优化后网络在参数减少7.5倍的情况下，误差降低最多达7.99%；或在参数减少83倍时几乎无精度损失。所有模型均可放入目标SoC（GreenWaves GAP8）的512 kB内存中，推理内存低于55 kB，平均延迟142毫秒，能耗7.25毫焦。患者特异性微调进一步提升精度达64%，实现可穿戴设备上全自主、低成本血压监测。
原文摘要 · Abstract (English)
Photoplethysmography (PPG)-based blood pressure (BP) estimation is a challenging task, particularly on resource-constrained wearable devices. However, fully on-board processing is desirable to ensure user data confidentiality. Recent deep neural networks (DNNs) have achieved high BP estimation accuracy by reconstructing BP waveforms or directly regressing BP values, but their large memory, computation, and energy requirements hinder deployment on wearables. This work introduces a fully automated DNN design pipeline that combines hardware-aware neural architecture search (NAS), pruning, and mixed-precision search (MPS) to generate accurate yet compact BP prediction models optimized for ultra-low-power multicore systems-on-chip (SoCs). Starting from state-of-the-art baseline models on four public datasets, our optimized networks achieve up to 7.99% lower error with a 7.5x parameter reduction, or up to 83x fewer parameters with negligible accuracy loss. All models fit within 512 kB of memory on our target SoC (GreenWaves' GAP8), requiring less than 55 kB and achieving an average inference latency of 142 ms and energy consumption of 7.25 mJ. Patient-specific fine-tuning further improves accuracy by up to 64%, enabling fully autonomous, low-cost BP monitoring on wearables.
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。