Diagnosis of Covid-19 using optimized convolutional neural network
Author(s):
Article Type:
Research/Original Article (بدون رتبه معتبر)
Abstract:
According to the report of the World Health Organization, corona disease is the most dangerous and contagious disease in the world. Currently, the most common method used to diagnose corona disease is the polymer chain reaction laboratory technique of reverse transcription, but since this method requires time to confirm the presence of the virus in the laboratory and also due to the unavailability of diagnostic kits and its high costs, Suspected corona virus patients cannot be identified and treated in time; This, in turn, can increase the likelihood of spreading the disease.Another diagnostic method is the use of X-ray chest imaging technique as well as chest computed tomography scan. Also, the use of deep learning methods can be very important for faster and more accurate diagnosis of the lung problems of the corona virus.In this study, using optimized deep convolutional networks based on X-ray images, patients with corona virus were diagnosed.In this article, using the optimized convolutional neural network of healthy people and those with corona, with 10-Fold cross-validation, average accuracy of 98.9% and average sensitivity of 96.5% were obtained.According to the obtained results, it can be said that the proposed method has the ability to separate healthy and unhealthy signals with acceptable accuracy.
Language:
English
Published:
Journal of Artificial Intelligence in Electrical Engineering, Volume:11 Issue: 44, Winter 2023
Pages:
25 to 32
https://www.magiran.com/p2613202
سامانه نویسندگان
مقالات دیگری از این نویسنده (گان)
-
Diagnosing diabetic retinopathy using retinal blood vessel examination based on convolution neural network
Mohammad Fatehi *, , Mohammad Moradi, Pedram Ravanbakhsh
Journal of Artificial Intelligence in Electrical Engineering, Summer 2022 -
Arrhythmia Classification Improvement by Individually Mapping the Feature Space of each patient
Hamid Shafaatfar, *, Morteza Valizadeh, MohamadHosein Fatehi
Iranian Journal of Biomedical Engineering,