|
INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016 open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15 |
Imp Links for Author
Imp Links for Reviewer
Research Area
Subscribe IJSDR
Visitor Counter
Copyright Infringement Claims
Indexing Partner
|
Published Paper Details
|
|
| Paper Title: | Multi-Scale and Context Aware Optimized Glucose Forecasting Using Neural Network |
| Authors Name: | SWEDHA K , Mr.D.RAJESH , JASHINI J , MITHRA C |
| Unique Id: | IJSDR2304078 |
| Published In: | Volume 8 Issue 4, April-2023 |
| Abstract: | Diabetes is a chronic illness that affects a sizable portion of the global population. For diabetic patients to keep their blood sugar levels within the normal range, accurate blood glucose prediction is crucial. In this study, we employ a well-known data-driven prediction algorithm that exclusively uses previous glucose measurements as input for multi-step predictions. Recently, deep learning has been used in medical research and healthcare to produce cutting-edge outcomes in a variety of tasks, including disease diagnosis and patient condition prediction, among others. We describe a deep learning model that can forecast glucose levels for simulated patient situations with the highest level of accuracy. This paper presents the findings of a study on LSTM-based blood glucose level forecasting systems for individuals with insulin-dependent diabetes. For both continuous subcutaneous glucose measurements and continuous subcutaneous insulin injections, forecasts are created. On the accuracy of forecasts, the impacts of the network architecture, neuronal count, training algorithm, and tapping delay line were examined. The research is a part of the work being done to create an algorithm for figuring out the right amount of insulin to take. This algorithm will be a closed-loop system that performs artificial tasks and works in conjunction with the continuous glucose monitoring and insulin pump devices. The gradient disappearing or exploding problem was solved by developing a cell based network architecture. The hidden neurons used in traditional neural networks are replaced by a hidden layer that is created by the cell. The input is processed locally by the neural network of the hidden layer node. When the input is close to the central range of the base function, the buried layer node will produce a sizeable output. |
| Keywords: | Long Short Term Memory, future glucose forecast, cell-based network. |
| Cite Article: | "Multi-Scale and Context Aware Optimized Glucose Forecasting Using Neural Network", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.8, Issue 4, page no.414 - 417, April-2023, Available :http://www.ijsdr.org/papers/IJSDR2304078.pdf |
| Downloads: | 000337214 |
| Publication Details: | Published Paper ID: IJSDR2304078 Registration ID:204525 Published In: Volume 8 Issue 4, April-2023 DOI (Digital Object Identifier): Page No: 414 - 417 Publisher: IJSDR | www.ijsdr.org ISSN Number: 2455-2631 |
|
Click Here to Download This Article |
|
| Article Preview | |
|
|
|
Major Indexing from www.ijsdr.org
| Google Scholar | ResearcherID Thomson Reuters | Mendeley : reference manager | Academia.edu |
| arXiv.org : cornell university library | Research Gate | CiteSeerX | DOAJ : Directory of Open Access Journals |
| DRJI | Index Copernicus International | Scribd | DocStoc |
Track Paper
Important Links
Conference Proposal
ISSN
 |
 |
DOI (A digital object identifier)
  Providing A digital object identifier by DOI How to GET DOI and Hard Copy Related |
Open Access License Policy
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
|
 |
 |
 |
Social Media
Indexing Partner |
|||
| Copyright © 2024 - All Rights Reserved - IJSDR | |||
Facebook Twitter Instagram LinkedIn