Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

A low Q-factor compact wideband microstrip patch antenna with stabilized gain for 5G and IoT applications.

Scientific reports·2026

Same author

A hybrid GAN-PDE framework with diffusion-guided residual attention for MRI brain image denoising.

Computational biology and chemistry·2026

Same author

Design-Expert Assisted Formulation Development, Optimization, and Evaluation of Selegiline and Biochanin A Loaded Self-Nanoemulsifying Drug Delivery System.

Drug development research·2026

Same author

A systematic review of transformer-enhanced UNet architectures for 3D medical image segmentation: Trends, challenges, and the ATD-TᵣEE<sub>v</sub> framework.

Computational biology and chemistry·2026

Same author

CFTR mRNA-Based Gene Therapy for Cystic Fibrosis: A Mutation-Agnostic Strategy to Restore Ion Transport Function.

Current gene therapy·2026

Same author

Wideband patch antenna with enhanced gain stability for sub-6 GHz 5G applications.

Scientific reports·2026

Search research articles

Related Experiment Video

Updated: Jun 28, 2025

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression

Published on: November 8, 2019

Non-invasive glucose prediction and classification using NIR technology with machine learning.

M Naresh¹, V Siva Nagaraju², Sreedhar Kollem³

¹School of Electronics Engineering, VIT-AP University, Amaravti, Guntur, 522241, Andhra Pradesh, India.

|April 11, 2024

Summary

This study introduces a dual wavelength near-infrared (NIR) system for accurate, non-invasive blood glucose monitoring. The system achieved high accuracy, comparable to traditional methods, offering a cost-effective solution for diabetes management.

Keywords:

Absorbance Classification Detectors Glucose Infrared Machine learning Noninvasive Regression Spectroscopy

More Related Videos

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Published on: June 28, 2016

Near Infrared Optical Projection Tomography for Assessments of β-cell Mass Distribution in Diabetes Research

Near Infrared Optical Projection Tomography for Assessments of β-cell Mass Distribution in Diabetes Research

Published on: January 12, 2013

Related Experiment Videos

Last Updated: Jun 28, 2025

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression

Published on: November 8, 2019

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Published on: June 28, 2016

Near Infrared Optical Projection Tomography for Assessments of β-cell Mass Distribution in Diabetes Research

Near Infrared Optical Projection Tomography for Assessments of β-cell Mass Distribution in Diabetes Research

Published on: January 12, 2013

Area of Science:

Biomedical Engineering
Medical Devices
Optical Sensing

Background:

Accurate blood glucose monitoring is crucial for diabetes management.
Current methods like finger prick tests are invasive and can be inconvenient.
Non-invasive glucose detection methods offer a promising alternative for improved patient compliance.

Purpose of the Study:

To develop and evaluate a dual wavelength short near-infrared (NIR) system for accurate, non-invasive glucose level detection.
To assess the system's performance against a reference finger prick glucose device.
To utilize advanced machine learning algorithms for glucose level prediction and classification.

Main Methods:

A dual wavelength short NIR spectroscopy system was designed and implemented.
Real-time blood glucose samples were collected and analyzed.
A feed forward neural network (FFNN) regression model was used for glucose level prediction.
Surveillance Error Grid (SEG) analysis was performed for clinical accuracy assessment.
Multilayer Perceptron (MLP) and K-Nearest Neighbors (KNN) classifiers were employed for glucose level classification.

Main Results:

The FFNN regression model demonstrated a high coefficient of determination (R²) of 0.99.
Key error metrics included Mean Absolute Error (MAE) of 2.49 mg/dl, Root Mean Square Error (RMSE) of 3.02 mg/dl, Mean Absolute Percentage Error (MAPE) of 1.94%, and Mean Squared Error (MSE) of 9.16.
SEG analysis confirmed that the system's measurements fall within clinically acceptable ranges.
MLP and KNN classifiers achieved a 99% accuracy in classifying glucose levels.

Conclusions:

The developed dual wavelength short NIR system provides a highly accurate and non-invasive method for blood glucose monitoring.
The system's performance, validated by FFNN regression and classification, is comparable to traditional invasive methods.
This technology offers a cost-effective and convenient solution for continuous glucose monitoring, potentially improving diabetes care.