Exploration of Low-Power Flexible Stress Monitoring Classifiers for Conformal Wearables

2025-08-27

AI Summary

Current stress monitoring relies on intermittent, rigid wearable devices, hindering long-term continuous use. While flexible electronics (FE) offer advantages in weight and cost, integrating high-accuracy, low-power machine learning (ML) classifiers onto FE substrates remains constrained by integration density and energy-efficiency bottlenecks. This work presents the first systematic exploration of the design space encompassing over 1,200 ML classifiers tailored for FE platforms. We propose a co-optimization framework combining FE-aware feature selection and neural simplification, alongside custom low-precision arithmetic circuits. The resulting flexible stress classifier achieves >92% classification accuracy while reducing power consumption by 3.8× and silicon area by 4.1× compared to state-of-the-art solutions. This advancement establishes a practical, hardware-intelligent paradigm enabling continuous, real-time, and comfortable psychological stress monitoring.

Technology Category

• Machine Learning: Hardware-aware ML
• Humans and AI: Human-in-the-loop Machine Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

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.

Problem

• Designing low-power flexible classifiers for stress monitoring
• Overcoming integration and power constraints in flexible electronics
• Exploring machine learning classifiers for real-time wearable stress detection

Innovation

• Low-power flexible stress classifiers exploration
• Customized circuits with low-precision arithmetic
• Neural simplification algorithms for hardware efficiency