Bachelor and Master Theses

To apply for conducting this thesis, please contact the thesis supervisor(s).
Title: Enhanced PPGFeat: Expanding Capabilities for Comprehensive PPG Analysis.
Subject: Computer science, Embedded systems, Software engineering, Innovation och design
Level: Basic
Description:

Biomedical signal processing is a critical component in modern healthcare, extracting valuable insights from physiological signals like the Photoplethysmogram (PPG). PPG, a non-invasive optical technique, provides information about blood volume changes and monitors various aspects of health, including cardiovascular conditions. Its potential lies in early detection and continuous monitoring of diseases.

PPGFeat is a valuable MATLAB toolbox that provides foundational tools for PPG signal preprocessing and feature extraction. To further empower researchers and clinicians, there's a need to expand PPGFeat's capabilities to handle diverse data sources, implement advanced signal processing techniques, and provide a more user-friendly experience.

Motivation:

  • This project aims to enhance PPGFeat significantly by expanding its functionality to support a wider range of research and clinical applications.
  • By improving its data handling, preprocessing, and feature extraction capabilities, we can provide a more versatile and powerful tool for PPG analysis.
  • The goal is to create a more robust and user-friendly toolbox that accelerates cardiovascular research.

Project Overview:

  • This project will focus on enhancing the PPGFeat toolbox by:

    • Database Integration: Implementing functionality to import PPG data from multiple publicly available databases.
    • Expanded Preprocessing: Adding a wider range of preprocessing algorithms, including options to integrate external, publicly available preprocessing tools.
    • Enhanced Feature Extraction: Developing new algorithms to extract a more comprehensive set of features from PPG waveforms.
    • Cross-Platform Compatibility: Ensuring the toolbox functions seamlessly on Windows and macOS operating systems.
    • GUI Enhancement: Redesigning and improving the graphical user interface (GUI) to incorporate new features and improve usability.
    • Multi-Mode Analysis: implementing modes to support single waveform analysis and overall data analysis of longer recordings.
    • Long Waveform Support: Ensuring the toolbox can accept long waveform inputs and then automatically perform preprocessing and feature extraction.
    • Feature Table Output: ensuring that the final output of the tool is a features table

References:

  • Abdullah S, Hafid A, Folke M, Lindén M and Kristoffersson A (2023) PPGFeat: a novel MATLAB toolbox for extracting PPG fiducial points. Front. Bioeng. Biotechnol. 11:1199604. doi: 10.3389/fbioe.2023.1199604
  • S. Abdullah, A. Hafid, M. Lindén, M. Folke and A. Kristoffersson, "Machine Learning-Based Classification of Hypertension using CnD Features from Acceleration Photoplethysmography and Clinical Parameters," 2023 IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS), L'Aquila, Italy, 2023, pp. 923-924, doi: 10.1109/CBMS58004.2023.00344.
  • The 2023 wearable photoplethysmography roadmap. DOI 10.1088/1361-6579/acead2
Start date:
End date:
Prerequisites:

Knowledge of Python or Matlab, Signal processing. A basic understanding of biosignals is beneficial.

Proficiency in English.

IDT supervisors: Saad Abdullah
Examiner:
Comments:

For further information, please contact saad.abdullah@mdu.se

Company contact: