Predicting vasovagal syncope for paraplegia patients using average weighted ensemble technique
Journal of Mobile Multimedia
; 18(1):135-162, 2022.
Article
in English
| Scopus | ID: covidwho-1404117
ABSTRACT
Vasovagal syncope (VVS) refers to fainting of people with a drop in blood flow to the brain more serious disease in paraplegia patients. Precognitive diagnoses are characterized by lightheadedness, nausea, severe fatigue, and an elevated heart rate. As a result, it’s important to seek care as soon as possible after experiencing syncope. Since receiving a correct diagnosis and appropriate care, the majority of patients may avoid complications with syncope. Syncope appears to be a sign of COVID 19 in people with coronary artery disease. Furthermore, a sudden heart attack might result in acute syncope. In a few circumstances, machine learning classification techniques may not be precise. For paraplegia patients, prediction vasovagal syncope needs more precise results in order to save their lives. The aim of this paper is to use the ensemble technique to improve the accuracy of conventional machine learning algorithms. EEG (ElectroEncephaloGram) brainwave dataset from kaggle is used to implement it. The accuracy of the proposed AWET algorithm is 82%. It improves the accuracy by 17% compare to Support Vector Machine, Random Forest, Naive Bayes, and MultiLayer Perceptron classifiers. © 2021 River Publishers
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Type of study:
Prognostic study
Language:
English
Journal:
Journal of Mobile Multimedia
Year:
2022
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS