Scholarlink

Objective <p>This research aims to develop a highly sensitive, non-invasive method for early detection and management of diabetes mellitus using optical sensor technology and Machine Learning (ML) models.</p> Impact statement <p>The study introduces the innovative use of the Fibre Braggs Grating (FBG) sensor and an Artificial Neural Network (ANN) -based model to accurately measure glucose levels, providing a rapid and precise diagnostic tool that improves patient comfort and diabetes management.</p> Introduction <p>Diabetes mellitus is a chronic condition that requires timely diagnosis and effective management to prevent complications. Traditional methods for monitoring glucose levels can be invasive and uncomfortable for patients. This study leverages the FBG sensor's ability to detect resonance wavelength shifts in response to varying glucose concentrations, offering a novel approach for non-invasive glucose measurement.</p> Method <p>The researchers employed the FBG sensor to analyze glucose levels in biological samples, such as urine and blood. They used a Couple Mode Theory model to predict the Refractive Index (RI) at different amplitudes and wavelengths, which was then used to infer the glucose concentration. An ANN-based model was implemented to enhance the accuracy and reliability of the measurements.</p> Results <p>The study demonstrated high precision in measuring glucose levels, with the maximum wavelength shift observed being 1.41654 for an RI of 1.339. This non-invasive approach successfully identified glucose concentrations in both urine and blood samples.</p> Conclusion <p>The findings highlight the potential of the FBG optical sensor combined with ML models as a promising solution for early detection and management of diabetes mellitus. This method significantly improves patient comfort and provides a reliable, accurate tool for monitoring glucose levels.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Diabetic detection through optical biosensor using artificial neural network model

  • 期刊论文

  • 发表日期：

    2025年9月17日

查看全文
  • Soni Gupta,
  • Sumita Mishra,
  • Bhupesh Kumar Singh,
  • Ayush Singh Rajput,
  • Sandip Kumar Roy

摘要

Objective

This research aims to develop a highly sensitive, non-invasive method for early detection and management of diabetes mellitus using optical sensor technology and Machine Learning (ML) models.

Impact statement

The study introduces the innovative use of the Fibre Braggs Grating (FBG) sensor and an Artificial Neural Network (ANN) -based model to accurately measure glucose levels, providing a rapid and precise diagnostic tool that improves patient comfort and diabetes management.

Introduction

Diabetes mellitus is a chronic condition that requires timely diagnosis and effective management to prevent complications. Traditional methods for monitoring glucose levels can be invasive and uncomfortable for patients. This study leverages the FBG sensor's ability to detect resonance wavelength shifts in response to varying glucose concentrations, offering a novel approach for non-invasive glucose measurement.

Method

The researchers employed the FBG sensor to analyze glucose levels in biological samples, such as urine and blood. They used a Couple Mode Theory model to predict the Refractive Index (RI) at different amplitudes and wavelengths, which was then used to infer the glucose concentration. An ANN-based model was implemented to enhance the accuracy and reliability of the measurements.

Results

The study demonstrated high precision in measuring glucose levels, with the maximum wavelength shift observed being 1.41654 for an RI of 1.339. This non-invasive approach successfully identified glucose concentrations in both urine and blood samples.

Conclusion

The findings highlight the potential of the FBG optical sensor combined with ML models as a promising solution for early detection and management of diabetes mellitus. This method significantly improves patient comfort and provides a reliable, accurate tool for monitoring glucose levels.