Towards a Machine Learning-Based Digital Twin for Non-Invasive Human Bio-Signal Fusion

Izaldein Al-Zyoud, Fedwa Laamarti, Xiaocong Ma, Diana Tobón, Abdulmotaleb El Saddik

Research output: Contribution to journalArticlepeer-review

13 Scopus citations

Abstract

Human bio-signal fusion is considered a critical technological solution that needs to be advanced to enable modern and secure digital health and well-being applications in the metaverse. To support such efforts, we propose a new data-driven digital twin (DT) system to fuse three human physiological bio-signals: heart rate (HR), breathing rate (BR), and blood oxygen saturation level (SpO2). To accomplish this goal, we design a computer vision technology based on the non-invasive photoplethysmography (PPG) technique to extract raw time-series bio-signal data from facial video frames. Then, we implement machine learning (ML) technology to model and measure the bio-signals. We accurately demonstrate the digital twin capability in the modelling and measuring of three human bio-signals, HR, BR, and SpO2, and achieve strong performance compared to the ground-truth values. This research sets the foundation and the path forward for realizing a holistic human health and well-being DT model for real-world medical applications.

Original languageEnglish
Article number9747
JournalSensors
Volume22
Issue number24
DOIs
StatePublished - Dec 2022

Keywords

  • bio-signal fusion
  • computer vision
  • digital health
  • digital twin
  • machine learning
  • metaverse

Product types of Minciencias

  • A1 article - Q1

Fingerprint

Dive into the research topics of 'Towards a Machine Learning-Based Digital Twin for Non-Invasive Human Bio-Signal Fusion'. Together they form a unique fingerprint.

Cite this