Afficher la notice abrégée
dc.contributor.author |
NAIDJA, Hanane |
|
dc.date.accessioned |
2023-11-26T09:51:12Z |
|
dc.date.available |
2023-11-26T09:51:12Z |
|
dc.date.issued |
2023 |
|
dc.identifier.uri |
http://dspace.univ-guelma.dz/jspui/handle/123456789/15021 |
|
dc.description.abstract |
After the explosion of data worldwide in recent years, all fields have been invaded by
the "Big Data" technology and have faced its challenges. The medical field has been no
exception and has faced an even greater challenge : the problem of missing data.
In this work, we focus on the analysis of Medical Big Data to predict future trends and
behaviors of data with high reliability in the context of missing data treatment. Missing
data is very common in the medical field and unfortunately leads to immense diagnostic
difficulties. Their treatment is also very sensitive since people’s lives depend on it.
The goal of this work is to demonstrate the importance of learning methods in the treat-
ment of missing data in the medical field and to propose an intelligent data imputation
system based on deep learning methods. Finally, the highly satisfactory results obtained
from the combination of different methods applied to two Medical Datasets have allowed
us to highlight the significance of the proposed model. |
en_US |
dc.language.iso |
fr |
en_US |
dc.publisher |
University of Guelma |
en_US |
dc.subject |
Big Data, Medical Dataset, Analytical Methods, Machine Learning, Deep Learning, Fuzzy K-means, Generative Antagonist Network |
en_US |
dc.title |
Traitement prédictif des données manquantes médicales par méthode d’apprentissage |
en_US |
dc.type |
Working Paper |
en_US |
Fichier(s) constituant ce document
Ce document figure dans la(les) collection(s) suivante(s)
Afficher la notice abrégée