ABSTRACT
As a result of the COVID-19 pandemic, medical examinations (RTPCR, X-ray, CT-Scan, etc.) may be required to make a medical decision. COVID-19's SARS-CoV-2 virus infects and spreads in the lungs, which can be easily recognized by chest X-rays or CT scans. However, along with COVID-19 instances, cases of another respiratory ailment known as Pneumonia began to rise. As a result, clinicians are having difficulty distinguishing between COVID-19 and Pneumonia. So, more tests were required to identify the condition. After a few days, the COVID-19 SARS-CoV-2 virus multiplied in the lungs, causing pneumonia and COVID-19 named Novel Corona virus infected Pneumonia. We employ Machine Learning and Deep Learning models to predict diseases such as COVID-19 Positive, COVID-19 Negative, and Viral Pneumonia in this research. A dataset of data is used in a Machine Learning model. A dataset of 120 images was used in the Machine Learning model. By extracting eight statistical elements from an image texture, we calculated accuracy. Adaboost, Decision Tree & Naive Bayes have overall accuracy of 88.46%, 86.4% and 80%, respectively. When we compared the algorithms, Adaboost algorithm performs the best, with overall accuracy of 88.46%, sensitivity of 84.62%, specificity of 92.31%, F1-score of 88% and Kappa of 0.8277. VGG16 Architecture is used in CNN model for 838 images in Deep Learning model. The model's total accuracy is 99.17 %. © 2022 IEEE.
ABSTRACT
The COVID-19 Coronavirus (SARS-CoV-2), has caused destruction all around the world, since December 2019. It is still managing to grow at an unprecedented scale. It was declared as a health emergency for the entire globe by the World Health Organization (WHO) in January 2022. The virus continues to impact the lives of millions of people. An early detection system warning about the repercussions of the virus at a county level can be favorable for the residents as well and aid the government to enforce appropriate safety measures. This research aims at modeling such a warning system which predicts the positivity rate of COVID-19 for a geographical location. The proposed solution uses supervised machine learning techniques such as Random Forest, Linear Regression, Naive Bayes, and Gradient Boosting Regression. The prediction is made based on the analysis of the past data in each time frame with temporal input such as the population of the area, number of tests conducted, number of positive tests, reported cases in that area among others. The Gradient Boosting algorithm outperforms all the other algorithms used in this research. Machine learning based recommendation system for COVID-19 spread can help the public and government to take necessary precautions for suppressing its effect. The proposed modeling approach provides a reliable tool to predict COVID-19 transmission with an accuracy of 99.4%. © 2022 IEEE.