Skip to content
 
 

Latest commit

 

History

2 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 

Repository files navigation

PuLsE: Accurate and Robust Ultrasound-Based Continuous Heart-Rate Monitoring on a Wrist-Worn IoT Device

project-logo

Heart rate extraction with A-Mode ultrasound

Developed with the software and tools below.
Python pandas NumPy SciPy Jupyter YAML tqdm C Make CMSIS-DSP ST HAL


Table of Contents:


Overview

In this research paper, we delve into the feasibility of extracting heart rate from the wrist with ultrasound signals in a wearable scenario by using a single ultrasound transducer in A-Mode (amplitude mode). We first wanted to determine the optimal transducer placement on the wrist, so we collected a dataset on 10 healthy subjects in three differentn wrist positions. A ECG chest belt has been used as ground truth. We employ an analog envelope circuit to reduce the bandwidth of the ultrasound signal: this reduction enables the signal to be acquired and processed by a common off-the-shelf (COTS) microcontroller (MCU). Both raw and enveloped ultrasound echos are collected and analysed.

Our work introduces a proof-of-concept wearable ultrasound system that achieves high-accuracy heart rate extraction. We address considerations related to power consumption, computation, and memory complexities. Notably, our approach leverages low-power and energy-efficient ultrasound technology, demonstrating ECG-level accuracy in heart rate extraction across a sample of ten individuals.


Repository structure

This repo is divided in two main parts, each contained in a separate folder. Inside each folder there is a README.md file guiding the reader through its content and providing the steps need to run the code/experiments and reproduce the results of the paper.

The folders are the following:

  • Dataset analysis: The dataset analysis repo contains the instruction to download the dataset collected in this work and the code to reproduce the results showed in the paper.
  • MCU-ADC-DSP: The MCU-ADC-DSP repo contains the code to be run on the MCU to acquire the ultrasound signal and run the digital signal processing (DSP) onboard to extract the heart rate.


License

This project is licensed under the Apache License 2.0. For more details, refer to the LICENSE file.


Acknowledgments

Publication links: ArXiv link IEEE IoT Journal

Please cite as:

Giordano, M., Leitner, C., Vogt, C., Benini, L., & Magno, M. (2024). PuLsE: Accurate and Robust Ultrasound-based Continuous Heart-Rate Monitoring on a Wrist-Worn IoT Device.


About

Repository containing Python scripts for data analysis, C code for the MCU, and the setup's 3D files to extract heart rate from ultrasound data.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors