Robust and Energy-efficient PPG-based Heart-Rate Monitoring

TL;DR

This paper introduces a hardware-efficient TCN-based algorithm for robust PPG heart-rate monitoring that outperforms previous methods and is suitable for deployment on low-power MCUs, addressing motion artifacts and energy constraints.

Contribution

It proposes a neural architecture search-driven TCN model optimized for edge deployment, improving accuracy and energy efficiency in PPG-based heart-rate estimation.

Findings

Achieved MAE of 3.84 BPM on PPGDalia dataset.

Deployed a small TCN with 5k parameters on STM32L4 MCU.

Latency of 17.1 ms and energy consumption of 0.21 mJ per inference.

Abstract

A wrist-worn PPG sensor coupled with a lightweight algorithm can run on a MCU to enable non-invasive and comfortable monitoring, but ensuring robust PPG-based heart-rate monitoring in the presence of motion artifacts is still an open challenge. Recent state-of-the-art algorithms combine PPG and inertial signals to mitigate the effect of motion artifacts. However, these approaches suffer from limited generality. Moreover, their deployment on MCU-based edge nodes has not been investigated. In this work, we tackle both the aforementioned problems by proposing the use of hardware-friendly Temporal Convolutional Networks (TCN) for PPG-based heart estimation. Starting from a single "seed" TCN, we leverage an automatic Neural Architecture Search (NAS) approach to derive a rich family of models. Among them, we obtain a TCN that outperforms the previous state-of-the-art on the largest PPG dataset available (PPGDalia), achieving a Mean Absolute Error (MAE) of just 3.84 Beats Per Minute (BPM). Furthermore, we tested also a set of smaller yet still accurate (MAE of 5.64 - 6.29 BPM) networks that can be deployed on a commercial MCU (STM32L4) which require as few as 5k parameters and reach a latency of 17.1 ms consuming just 0.21 mJ per inference.