ABSTRACT
When the World Health Organization declared world pandemic in 2020 due to high propagation rate of the COVID-19, several government levels (municipalities, states and countries) initiated actions to try to fight the spread of the disease. Most of these actions where some sort of quarantine or urban mobility restrictions. To guide the governments' actions and decisions, several factors have to be considered, such as propagation and lethalness of the disease for each administrative region. However, die to the differences between urban regions, in Brazil, the final decision as to which actions to take were left to the municipalities. For this reason, o goal of this study is to, based on the official data available for the city of Rio de Janeiro, use Artificial Intelligence tools and Multicriteria Methods to identify the administrative regions that will require a higher level of attention in the event of a second wave of COVID-19. (English) [ FROM AUTHOR]
ABSTRACT
With the expansion of coronavirus in the World, the search for technology solutions based on the analysis and prospecting of diseases has become constant. The paper addresses a machine learning algorithms analysis used to predict and identify infected patients. For analysis, we use a multicriteria approach using the PROMETHEE-GAIA method, providing the structuring of alternatives respective to a set of criteria, thus enabling the obtaining of their importance degree under the perspective of multiple criteria. The study approaches a sensitivity analysis, evaluating the alternatives using the PROMETHEE I and II methods, along with the GAIA plan, both implemented by the Visual PROMETHEE computational tool, exploring numerical and graphical resources. The analysis model proves to be effective, guaranteeing the ranking of alternatives by inter criterion evaluation and local results with intra criterion evaluation, providing a transparent analysis concerning the selection of prediction algorithms to combat the COVID-19 pandemic.
ABSTRACT
The pandemic caused by the new coronavirus has brought to light a series of concerns for the Brazilian population and government departments due to the different costly consequences that it has generated. It has also mobilized different strategic fronts that plan and implement several mitigating measures against the virus. Besides, the search for solutions for adequate care for individuals in need of support has been constant. This work uses ELECTRE-MOr, a Multi-Criteria Decision Aid (MCDA) method, to support the logistic plan for the vaccine distribution throughout Brazil, essentially to remote areas. The method allows an objective and structured classification of ideal types of thermal boxes for the storage of immunobiological inside the Cold Chain, presenting the best alternative that maintains the quality of materials until the final destination and has the best cost-benefit. Currently, the ELECTRE-MOr model is under development in a computational tool in Python, allowing the use of the method intuitively and clearly, enabling professionals of any area of expertise to apply it.