EnhancePPG: Improving PPG-based Heart Rate Estimation with Self-Supervision and Augmentation

TL;DR

EnhancePPG introduces a self-supervised learning and data augmentation framework that significantly improves heart rate estimation accuracy from PPG signals in wearable devices without increasing inference latency.

Contribution

The paper proposes a novel self-supervised pre-training method combined with data augmentation to enhance PPG-based HR estimation models, requiring no additional labeled data.

Findings

Achieved a 12.2% reduction in HR estimation error on PPG-DaLiA dataset.

Improved state-of-the-art HR estimation accuracy from 4.03 BPM to 3.54 BPM.

Method maintains low inference latency suitable for wearable devices.

Abstract

Heart rate (HR) estimation from photoplethysmography (PPG) signals is a key feature of modern wearable devices for health and wellness monitoring. While deep learning models show promise, their performance relies on the availability of large datasets. We present EnhancePPG, a method that enhances state-of-the-art models by integrating self-supervised learning with data augmentation (DA). Our approach combines self-supervised pre-training with DA, allowing the model to learn more generalizable features, without needing more labelled data. Inspired by a U-Net-like autoencoder architecture, we utilize unsupervised PPG signal reconstruction, taking advantage of large amounts of unlabeled data during the pre-training phase combined with data augmentation, to improve state-of-the-art models' performance. Thanks to our approach and minimal modification to the state-of-the-art model, we improve the best HR estimation by 12.2%, lowering from 4.03 Beats-Per-Minute (BPM) to 3.54 BPM the error on PPG-DaLiA. Importantly, our EnhancePPG approach focuses exclusively on the training of the selected deep learning model, without significantly increasing its inference latency