Photoplethysmography Based Blood Glucose Estimation Using Convolutional Neural Networks

Saifeddin Alghlayini, Asmaa Hosni, Mohamed Atef

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

This paper introduces the design and measurements for non-invasive blood glucose level (BGL) estimation using a convolutional neural network (CNN) based on photoplethysmography (PPG). The prototype consists of a PPG sensor connected to a microcontroller (MCU) Arduino Nano 33 BLE Sense. The PPG-only based CNN model deployed on the MCU showed 89.28% of the predicted samples in zone A of a Clarke error grid (CEG). When the mean power spectrum feature from PPG signals was included, the results demonstrated an improvement in the accuracy to be 92.85%. The proposed system is real-time and non-invasive that can be used to replace the existing invasive glucometers.

Original languageEnglish
Title of host publication2023 Advances in Science and Engineering Technology International Conferences, ASET 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665454742
DOIs
Publication statusPublished - 2023
Event2023 Advances in Science and Engineering Technology International Conferences, ASET 2023 - Dubai, United Arab Emirates
Duration: Feb 20 2023Feb 23 2023

Publication series

Name2023 Advances in Science and Engineering Technology International Conferences, ASET 2023

Conference

Conference2023 Advances in Science and Engineering Technology International Conferences, ASET 2023
Country/TerritoryUnited Arab Emirates
CityDubai
Period2/20/232/23/23

Keywords

  • Blood Glucose Level (BGL)
  • Convolutional Neural Network (CNN)
  • Deep Learning
  • Machine Learning
  • Microcontroller (MCU)
  • Photoplethysmography (PPG)
  • Wearable Device

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment
  • Biomedical Engineering
  • Control and Optimization
  • Artificial Intelligence
  • Computer Science Applications
  • Decision Sciences (miscellaneous)
  • Fuel Technology

Fingerprint

Dive into the research topics of 'Photoplethysmography Based Blood Glucose Estimation Using Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this