A Cloud-Connected Digital System for type-1 Diabetes Prediction using Time series LSTM model

Authors

  • K. Priyadarshini Department of Electronics and Communication Engineering, K.Ramakrishnan College of Engineering, Samayapuram, Trichy, India
  • Alanoud Al Mazroa Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University (PNU), P.O. Box 84428, Riyadh 11671, Saudi Arabia
  • Mohammad Alamgeer Department of Information Systems, Applied College at Mahayil, King Khalid University, Saudi Arabia
  • V. Subashree Department of ECE, Saveetha Engineering College, Chennai, India

DOI:

https://doi.org/10.2478/msr-2024-0011

Keywords:

Adaptive Model Predictive Control (AMPC), Glucose-Insulin (GI), Lehman Based Diabetic Patient Model (LBDPM), Neural Network (NN), Neural Basis Expansion Analysis for Interpretable Time Series (N-BEATS)

Abstract

 Millions of people worldwide suffer from diabetes, a medical ailment that is spreading at an accelerating pace 4. Numerous studies demonstrate that risk factors that may arise from diabetes may be avoided by detecting the condition early. The health-care monitoring system has benefited greatly from the early diabetes prediction made possible by the integration of deep learning and machine learning algorithms. The objective of many early studies was to increase prediction model accuracy; however, deep learning algorithms often cannot fully use the potential of available datasets because they are too small. This study includes a very accurate deep learning model as well as a novel system that integrates cloud services and allows users to directly enhance an existing dataset, which can be used to increase the accuracy of deep learning techniques. Hence, LSTM model is opted with controller for efficient type-1 diabetes prediction. The experimental validation of the proposed NMPC_LSTM algorithm method is compared with other conventional deep learning algorithms. The proposed controller method attains excellent blood glucose set point tracking and the proposed algorithms give accuracy rates 98.95% for the data obtained. It outperforms other existing methods with an increase in the accuracy percentage compared with Benchmark Pima Indian Diabetes Datasets (PIDD).

Downloads

Published

13.04.2024

How to Cite

Priyadarshini, K., Al Mazroa, A., Alamgeer, M., & Subashree, V. (2024). A Cloud-Connected Digital System for type-1 Diabetes Prediction using Time series LSTM model. Measurement Science Review, 24(2), 83–87. https://doi.org/10.2478/msr-2024-0011

Similar Articles

<< < 1 2 3 4 5 6 7 8 9 10 > >> 

You may also start an advanced similarity search for this article.