UMP Institutional Repository

Non-Invasive Diabetes Level Monitoring System using Artificial Intelligence and UWB

Islam, Minarul and Sabira, Khatun and Shoumy, Nusrat Jahan and Ali, Md Shawkat and Mohamad Shaiful, Abdul Karim and Bari, Bifta Sama (2020) Non-Invasive Diabetes Level Monitoring System using Artificial Intelligence and UWB. In: 2nd International Conference on Cyber Security and Computer Science (ICONS 2020), 15-16 February 2020 , Dhaka, Bangladesh. pp. 376-387., 325. ISBN 978-3-030-52856-0

[img]
Preview
Pdf
Non-Invasive Diabetes Level Monitoring System1.pdf

Download (91kB) | Preview

Abstract

Diabetes is a silent-killer disease throughout the world. It is not cura-ble, therefore, regular blood glucose concentration levels (BGCL) monitoring is necessary to be healthy in a long run. The traditional way of BGCL measurement is invasive by pricking and collecting blood sample from human arm (or finger-tip), then measuring the level either using a glucometer or sending to laboratory. This blood collecting process produces significant discomfort to the patients, es-pecially to the children with type-A diabetes, resulting increased undetected-cases and health-complications. To overcome this drawbacks, a non-invasive ul-tra-wideband (UWB) BGCL measurement system is proposed here with en-hanced software module. The hardware can be controlled through the graphical user interface (GUI) of software and can execute signal processing, feature ex-traction, and feature classification using artificial intelligence (AI). As AI, cas-cade forward neural network (CFNN) and naïve bayes (NB) algorithms are in-vestigated, then CFNN with four independent features (skewness, kurtosis, vari-ance, mean-absolute-deviation) are found to be best-suited for BGCL estimation. A transmit (Tx) antenna was placed at one side of left-earlobe to Tx UWB sig-nals, and a receive (Rx) antenna at opposite side to Rx transmitted signals with BGCL marker. These signals are saved and used for AI training, validation and testing. The system with CFNN shows approximately 86.62% accuracy for BGCL measurement, which is 5.62% improved compared to other methods by showing its superiority. This enhanced system is affordable, effective and easy-to-use for all users (home and hospital), to reduce undetected diabetes cases and related mortality rate in near future.

Item Type: Conference or Workshop Item (Lecture)
Uncontrolled Keywords: UWB, Non-invasive Measurement, Blood Glucose Concentration Level, cascade forward neural network.
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Faculty/Division: Institute of Postgraduate Studies
Faculty of Electrical and Electronic Engineering Technology
Depositing User: Noorul Farina Arifin
Date Deposited: 21 Jul 2020 01:37
Last Modified: 04 Aug 2020 06:17
URI: http://umpir.ump.edu.my/id/eprint/28829
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item