0
research-article

Investigations on Multi-sensor based Non-invasive Blood Glucose Measurement System

[+] Author and Article Information
Jyoti Yadav

Instrumentation and Control Engineering Division, NSIT Full Mailing Address: Research Lab, Block -6, NSIT, Dwarka, New Delhi
bmjyoti@gmail.com

Asha Rani

Instrumentation and Control Engineering Division, NSIT Full Mailing Address: Research Lab, Block -6, NSIT, Dwarka, New Delhi
ashansit@gmail.com

Vijander Singh

Instrumentation and Control Engineering Division, NSIT Full Mailing Address: Research Lab, Block -6, NSIT, Dwarka, New Delhi
vijaydee@gmail.com

Bhaskar Mohan Murari

Department of Sensors and Biomedical Technology, VIT University, Vellore
bhaskarmurari@vit.ac.in

1Corresponding author.

ASME doi:10.1115/1.4036580 History: Received July 20, 2016; Revised March 13, 2017

Abstract

To reform diabetes management painless and reliable noninvasive blood glucose (NIBG) measurement technique has been explored since last three decades. In the present work photoplethysmogram (PPG) signal is used to measure the variations in blood glucose concentration. However, the literature reveals that physiological perturbations such as temperature, skin moisture and sweat cause poor accuracy of NIBG measurement. The task of minimizing the effect of these perturbations and to improve accuracy is an important research area. Therefore, along with PPG sensor, Galvanic Skin Response (GSR) and temperature sensors are also used to achieve more accurate NIBG measurement. The accuracy of the proposed Multi-sensor system is evaluated by pairing and comparing non-invasively measured data with invasively measured readings. The study is made on 50 non-diabetic subjects with BMI 27.3±3 kg/m2. Two machine learning techniques, i.e. Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) are used to estimate the glucose concentration from extracted data. The results reveal that the MAPE and correlation coefficient are significantly improved in comparison to the techniques reported in the literature.

Copyright (c) 2017 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In