Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 3 de 3
Add filters

Document Type
Year range
Artificial Intelligence and Big Data Analytics for Smart Healthcare ; : 209-224, 2021.
Article in English | Scopus | ID: covidwho-2075781


Currently, the most common disease is the new coronavirus disease identified as COVID-19. Various techniques to identifying the COVID-19 disease have been offered. Computer vision techniques are widely used to classify COVID-19 with the use of chest X-ray images. Rapid clinical results may prevent COVID-19 from spreading and help doctors treat patients under high workload conditions. As the normal diagnosis phase of illness with a laboratory test is time-consuming and requires a well-equipped laboratory, the X-ray imaging technique is a fast and cheap diagnostic tool for COVID-19. Machine learning methods can enhance the diagnosis of COVID-19 as a decision support platform for radiologists. This chapter utilizes various convolutional neural network (CNN) models, including pretrained models, to classify X-ray images into three classes: COVID-19, pneumonia, and normal. CNN, a form of deep neural networks that have become dominant in various computer vision tasks, attracts interest across various domains, including radiology. Pretrained models on ImageNet are good at detecting high-level features such as edges and patterns. These models understand certain representations of features, which can be reused. Also, deep classifiers have shown promising results in many kinds of work across various domains. We drew some useful results from these classifiers, which could be used faster when detecting COVID-19. Experimental results showed that the accuracy of the VGG19 classifier is 97.56%. © 2021 Elsevier Inc. All rights reserved.

5G IoT and Edge Computing for Smart Healthcare ; : 195-229, 2022.
Article in English | Scopus | ID: covidwho-2048807


Machine learning (ML) uses statistical theory to create models from data samples. Using the predictive and statistical models, computers can clean and curate the data, interpret and predict the outcomes of certainties (or uncertainties) with precise accuracy. Of course, the interpretation of the produced results and algorithmic solution designed for each problem needs to be fine-tuned and proficient for the target problem. Biomedical images relevant to different diseases are recorded from a body and are generally employed to diagnose precise physiological or pathological conditions. The objective of biomedical image analysis is exact modeling by using pattern recognition and computer vision to diagnose diseases by employing ML techniques. This chapter explains how artificial intelligence (AI) and ML techniques are utilized in disease diagnosis. An automated COVID-19 diagnosis approach based on deep feature extraction is also presented. After extracting features using deep transfer learning (DTL), the X-ray images are fed into the shallow ML model to diagnose COVID-19 from X-ray images. With chest X-ray, a patient can be identified as a potential COVID-19 patient and can be quarantined. X-ray equipment are already accessible in most hospitals, and already digitized. Since X-ray images are high dimensional data, a Convolutional Neural Network based feature extraction via transfer learning models are appropriate for the diagnosis of COVID-19. It may help an inpatient environment where the existing programs find it difficult to determine whether to keep the patient inward with other patients or separate them. This technique will also help classify patients with high COVID-19 risk who need to repeat testing with a false negative RT-PCR. © 2022 Elsevier Inc. All rights reserved.

Fractals ; 2020.
Article in English | Scopus | ID: covidwho-919094


SARS-CoV-2 is a deadly virus that has affected human life since late 2019. Between all the countries that have reported the cases of patients with SARS-CoV-2 disease (COVID-19), the United States of America has the highest number of infected people and mortality rate. Since different states in the USA reported different numbers of patients and also death cases, analyzing the difference of SARS-CoV-2 between these states has great importance. Since the generated RNA walk from the SARS-CoV-2 genome includes complex random fluctuations that also contain information, in this study, we employ the complexity and information theories to investigate the variations of SARS-CoV-2 genome between different states in the USA for the first time. The results of our analysis showed that the fractal dimension and Shannon entropy of genome walk significantly change between different states. Based on these results, we can conclude that the SARS-CoV-2 genomic structure significantly changes between different states, which is resulted from the virus evolution. Therefore, developing a vaccine for SARS-CoV-2 is very challenging since it should be able to fight various structures of the virus in different states. © 2020