Machine Learning Model to Study the Genetic Susceptibility of Patients with Sever Coronavirus Symptoms
2023 IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2023
; 2023.
Article
Dans Anglais
| Scopus | ID: covidwho-2325416
ABSTRACT
COVID 19 is constantly changing properties because of its contagious as an urgent global challenge, and there are no vaccines or effective drugs. Smart model used to measure and prevent the spread of COVID 19 continues to provide health care services is an urgent need. Previous methods to identify severe symptoms of coronavirus in the early stages, but they have failed to predict the symptoms of coronavirus in an accurate way and also take more time. To overcome these issues the effective severe coronavirus symptoms techniques are proposed. Initially, Gradient Conventional Recursive Neural Classifier based classification and Linear Discriminant Genetic Algorithm used feature selection, mutation, and cross-analysis of features of coronary symptoms. These methods are used to select optimized features and selected features, and then classified by neural network. This Gradient Conventional Recursive Neural Classifier selects features based on the correlation between features that reduce irrelevant features involved in the identification process of coronary symptoms. Gradient Conventional Recursive Neural Classifier based on each function, helping to maximize the correlation between the prediction accuracy of coronavirus symptoms. For this reason, it has always been recommended in an effort to increase the accuracy and reliability of diagnostics to use machine learning to design different classification models. © 2023 IEEE.
accuracy; feature selection; Gradient Conventional Recursive Neural Classifier; Linear Discriminant Genetic Algorithm; preprocessing; Classification (of information); COVID-19; Diagnosis; Genetic algorithms; Learning algorithms; Coronaviruses; Features selection; Genetic susceptibility; Linear discriminants; Machine learning models; Neural classifiers; Coronavirus
Texte intégral:
Disponible
Collection:
Bases de données des oragnisations internationales
Base de données:
Scopus
Type d'étude:
Étude pronostique
/
Essai contrôlé randomisé
Les sujets:
Vaccins
langue:
Anglais
Revue:
2023 IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2023
Année:
2023
Type de document:
Article
Documents relatifs à ce sujet
MEDLINE
...
LILACS
LIS