| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 12.7 MB | Adobe PDF |
Authors
Advisor(s)
Abstract(s)
The outbreak of tfe Severe Acute Respiratory Syndrome – Coronavirus 2 (SARS-CoV-2) – also known as COVID 19 has brought global insecurity and fear to our society. Every country in the worl figts together against the spread of this deadly disease with joining efforts. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention from authorities, wich are popular in the media.Officials around the world are using several outbreak prediction models for COVID-19 to make informe decisions and enforce relevant control measures. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. This work aims to show na explaratory data analysis od COVID-19 worlwide to understand the real threats and the subsequente planning of containment/mitigation actions. The machine learning models were used to study and understand the everyday exponential bahavior of the COVID-19 across the nations using real-time information from johns Hopkins University and, in particular, in Portugal, with real-time information from Portugal Health Ministry to predict future reachability. In this work, modeling diferente algorithms and evaluating their performance. These algorithms are Polynominal Regression, Support Vector Regression. For the Portuguese dataset, we modeled and evaluated the following algoritms’ performance: Linera Regression, Plynominal Regression, Support Vector Regression, Multilayer Perceptron, and Poly-MultilayerPerceptron. This work also compares three different countries (but very similar – Portugal, Spain and Italy). In the particular case of Portugal, the containment/mitigation actions used by the portuguese government were explored. A comparative analysis was also caried out between Portugal, Spain, and Italy, since the first reported case, in each country, over two months. We also study the effectiveness of mitigation measures, defined by the Portugues government, carried out by the health authorities and my fellow citizens. In the worldwide prediction of the first wave of COVID-19, the best model is the Polynominal Regression model (R-squared – 0.787, MAE – 540.39, RMSE – 782.14, nd the execution time is 0.16s), and in the second wave, the best model is Support Vector Regression (R-squared – 0.996, MAE – 17.41, RMSE 18.98, and the execution time is 0.35s). In the portuguese predictions of COVID-19 (diferente waves), the best model are Polynominal Regression, Multlayer Perceptron, and Poly-MultilayerPerceptron prediction models. In comparing three diferent countries (Portugal, Spain, and Italy), Portugal had the best performance in the testing and mitigation policies. In the study of effectiveness of mitigation measures, defined by the Portuguese government, as soon as the implementation of mitigation measures mores effective are the result of mitigation of the disease.
Description
Keywords
SARS-CoV-2 COVID-19 knowledge discovery in databases Data mining Machine learning algorithms