首个低功耗柔性压力检测分类器设计，兼顾实时性与可穿戴性
Exploration of Low-Power Flexible Stress Monitoring Classifiers for Conformal Wearables
- 探索1200+种柔性低功耗分类器，结合特征选择与神经网络简化
- 实现比现有方法更高的准确率，且功耗低、体积小、可贴合皮肤
- 适合长期压力监测的可穿戴设备开发者，尤其关注硬件效率者
传统压力监测依赖间歇性、症状导向的干预，难以满足持续、便捷、低成本的需求。现有先进方法多采用刚性硅基可穿戴设备，虽具备多任务能力，但未针对轻量化、柔性佩戴优化，实用性受限。相比之下，柔性电子（FE）具备柔韧性和低成本制造优势，支持实时压力监测电路。然而，由于集成与功耗限制，将复杂电路如机器学习（ML）分类器嵌入FE仍具挑战。此前研究已涉及柔性生物传感器和模数转换器（ADC），但针对压力检测的分类器设计仍不充分。本文首次系统探索低功耗柔性压力分类器的设计空间，涵盖多种机器学习分类器、特征选择与神经网络简化算法，构建超过1200种柔性分类器。为提升硬件效率，每种方案均设计专用低精度算术电路。实验结果表明，所提方法可在保持低功耗、小型化、贴合性的同时，实现高于当前技术的准确率，为实时压力监测提供可行路径。
原文摘要 · Abstract (English)
Conventional stress monitoring relies on episodic, symptom-focused interventions, missing the need for continuous, accessible, and cost-efficient solutions. State-of-the-art approaches use rigid, silicon-based wearables, which, though capable of multitasking, are not optimized for lightweight, flexible wear, limiting their practicality for continuous monitoring. In contrast, flexible electronics (FE) offer flexibility and low manufacturing costs, enabling real-time stress monitoring circuits. However, implementing complex circuits like machine learning (ML) classifiers in FE is challenging due to integration and power constraints. Previous research has explored flexible biosensors and ADCs, but classifier design for stress detection remains underexplored. This work presents the first comprehensive design space exploration of low-power, flexible stress classifiers. We cover various ML classifiers, feature selection, and neural simplification algorithms, with over 1200 flexible classifiers. To optimize hardware efficiency, fully customized circuits with low-precision arithmetic are designed in each case. Our exploration provides insights into designing real-time stress classifiers that offer higher accuracy than current methods, while being low-cost, conformable, and ensuring low power and compact size.
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。