Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Effectiveness of fermentation broth of <i>Cordyceps sinensis</i> for primary insomnia: a randomized clinical trial with digital health tool.

Frontiers in neurology·2025
Same author

Exhaled gas biomarkers: a non-invasive approach for distinguishing diabetes and its complications.

The Analyst·2025
Same author

Chinese Medicine in the Era of Artificial Intelligence: Challenges and Development Prospects.

The American journal of Chinese medicine·2025
Same author

Evaluating the Effectiveness and Safety of Home Facial Antiaging Beauty Devices Based on Meridian and Acupoint Theory.

Journal of cosmetic dermatology·2025
Same author

Development of a Portable Rapid Detection Method for Porcine Epidemic Diarrhea Virus Using Reverse Transcription-Recombinase-Aided Amplification Technology.

Animals : an open access journal from MDPI·2025
Same author

A Flexible Temperature Sensor Integrated at Needle Tip for In Situ Acupoint Temperature Monitoring.

Micromachines·2024

Related Experiment Video

Updated: Jul 11, 2025

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data
04:13

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Published on: November 13, 2019

12.2K

Glucose trend prediction model based on improved wavelet transform and gated recurrent unit.

Tao Yang1,2, Qicheng Yang1,2, Yibo Zhou3

  • 1College of Intelligent Medicine, Chengdu University of Traditional Chinese Medicine, Chengdu 610000, Sichuan, China.

Mathematical Biosciences and Engineering : MBE
|November 3, 2023
PubMed
Summary

This study introduces an improved wavelet transform denoising algorithm and an IWT-GRU model for accurate real-time glucose trend prediction using continuous glucose monitoring data, enhancing artificial pancreas functionality.

Keywords:
blood glucose trend predictioncontinuous glucose monitoringgated recurrent unitimproved wavelet transform

More Related Videos

Automatic Detection of Highly Organized Theta Oscillations in the Murine EEG
09:35

Automatic Detection of Highly Organized Theta Oscillations in the Murine EEG

Published on: March 10, 2017

9.2K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

775

Related Experiment Videos

Last Updated: Jul 11, 2025

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data
04:13

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Published on: November 13, 2019

12.2K
Automatic Detection of Highly Organized Theta Oscillations in the Murine EEG
09:35

Automatic Detection of Highly Organized Theta Oscillations in the Murine EEG

Published on: March 10, 2017

9.2K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

775

Area of Science:

  • Biomedical Engineering
  • Data Science
  • Artificial Intelligence

Background:

  • Continuous glucose monitoring (CGM) data is vital for artificial pancreas (AP) systems.
  • Accurate real-time glucose trend prediction is essential for effective glycemic control and preventing hypo/hyperglycemia.

Purpose of the Study:

  • To develop an improved wavelet transform threshold denoising algorithm for CGM data.
  • To propose a novel glucose trend prediction model (IWT-GRU) integrating this denoising technique with a Gated Recurrent Unit.
  • To evaluate the performance of the IWT-GRU model against other established models for glucose trend prediction.

Main Methods:

  • An improved wavelet transform threshold denoising algorithm was developed to address non-linearity and non-smoothness in CGM data.
  • The denoised CGM data was used to train and test the IWT-GRU model.
  • Performance was evaluated using Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R²).
  • Comparative analysis included Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Support Vector Regression (SVR), and Gated Recurrent Unit (GRU) models.

Main Results:

  • The improved wavelet transform algorithm effectively reduced distortion and enhanced feature extraction from CGM data, as evidenced by improved Mean Square Error (MSE) and Signal-to-Noise Ratio (SNR).
  • The IWT-GRU model significantly outperformed RNN, LSTM, SVR, and GRU in glucose trend prediction accuracy across various prediction horizons.
  • At a 45-minute prediction horizon, IWT-GRU achieved an RMSE of 0.5537 mmol/L, MAPE of 2.2147%, and R² of 0.989, with an average runtime of 37.2 seconds.

Conclusions:

  • The proposed IWT-GRU model demonstrates superior performance in glucose trend prediction compared to existing methods.
  • The improved wavelet transform denoising is effective in preparing CGM data for accurate predictive modeling.
  • This advancement holds significant potential for improving the efficacy and safety of artificial pancreas systems.