A Data-Driven Compressive Sensing Framework Tailored For Energy-Efficient Wearable Sensing

TL;DR

This paper introduces a data-driven compressive sensing framework for energy-efficient wearable health sensors that learns personalized signal features, significantly improving compression and reconstruction quality over traditional methods.

Contribution

It presents a novel co-training approach that optimizes sensing matrices and dictionaries based on individual physiological signals, enhancing performance in wearable sensing applications.

Findings

Reduces isometry constant by 86% at 10x compression ratio.

Improves reconstructed signal-to-noise ratio by 15dB.

Demonstrates superior performance over conventional model-driven CS methods.

Abstract

Compressive sensing (CS) is a promising technology for realizing energy-efficient wireless sensors for long-term health monitoring. However, conventional model-driven CS frameworks suffer from limited compression ratio and reconstruction quality when dealing with physiological signals due to inaccurate models and the overlook of individual variability. In this paper, we propose a data-driven CS framework that can learn signal characteristics and personalized features from any individual recording of physiologic signals to enhance CS performance with a minimized number of measurements. Such improvements are accomplished by a co-training approach that optimizes the sensing matrix and the dictionary towards improved restricted isometry property and signal sparsity, respectively. Experimental results upon ECG signals show that the proposed method, at a compression ratio of 10x, successfully reduces the isometry constant of the trained sensing matrices by 86% against random matrices and improves the overall reconstructed signal-to-noise ratio by 15dB over conventional model-driven approaches.