Deep Harmonic Finesse: Signal Separation in Wearable Systems with Limited Data

TL;DR

Deep Harmonic Finesse (DHF) is a novel deep learning method designed for separating quasi-periodic signals in wearable systems with limited data, leveraging prior time-frequency knowledge and pattern alignment.

Contribution

The paper introduces DHF, a deep harmonic neural network with pattern alignment for effective signal separation using minimal data in wearable physiological monitoring.

Findings

Achieves 26% average improvement in signal-to-distortion ratio on synthesized data.

Reduces mean squared error by 80% on synthesized data.

Increases correlation accuracy by 80.5% in in vivo fetal monitoring.

Abstract

We present a method, referred to as Deep Harmonic Finesse (DHF), for separation of non-stationary quasi-periodic signals when limited data is available. The problem frequently arises in wearable systems in which, a combination of quasi-periodic physiological phenomena give rise to the sensed signal, and excessive data collection is prohibitive. Our approach utilizes prior knowledge of time-frequency patterns in the signals to mask and in-paint spectrograms. This is achieved through an application-inspired deep harmonic neural network coupled with an integrated pattern alignment component. The network's structure embeds the implicit harmonic priors within the time-frequency domain, while the pattern-alignment method transforms the sensed signal, ensuring a strong alignment with the network. The effectiveness of the algorithm is demonstrated in the context of non-invasive fetal monitoring using both synthesized and in vivo data. When applied to the synthesized data, our method exhibits significant improvements in signal-to-distortion ratio (26% on average) and mean squared error (80% on average), compared to the best competing method. When applied to in vivo data captured in pregnant animal studies, our method improves the correlation error between estimated fetal blood oxygen saturation and the ground truth by 80.5% compared to the state of the art.