Modelos computacionais fuzzy tipo-2 intervalar para avaliar efeitos da poluição do ar em crianças

• Autor(a) principal: Almeida, Paula Ferreira de [UNESP]
• Data de Publicação: 2018
• Tipo de documento: Trabalho de conclusão de curso
• Idioma: por
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://hdl.handle.net/11449/203510; http://www.athena.biblioteca.unesp.br/exlibris/bd/capelo/2019-06-25/000917247.pdf
• topic: Lógica difusa; Ar - Poluição; Mudanças climáticas; Fuzzy logic

Exposure to air pollutants combined with climatic factors may be associated with hospitalizations for respiratory diseases of children. This work presents the construction of a computational model using the interval-type fuzzy type-2 logic. The model has four inputs, each with two pertinence functions, thus obtaining 16 rules, and the five-function output, based on the Mamdani method to estimate the number of hospitalizations for respiratory diseases in children according to air pollutants and climatic variables. The study was carried out in the period of 2011 and 2013, in the city of São José do Rio Preto, São Paulo, Brazil. The inputs PM10, NO2, temperature and wind speed were obtained from the database of Cetesb (Environmental Company of the State of São Paulo) and the number of hospitalizations for respiratory diseases was obtained from Datasus (Department of Information Technology of the Single System of health). During the study period, 1015 hospitalizations were recorded, with an average of 1.53 (dp = 1.55), and the mean of the pollutants was 36μg / m3 of PM10 and 51μg / m3 of NO2. Compared to the fuzzy type-1 model developed with the same database, this model was better, because it obtained a greater correlation of Pearson. The model proved to be effective in predicting the number of hospitalizations and can be used as the basis of a specialist system, which can assist the municipal manager in assessing the risk of hospitalizations due to air pollutants and climatic factors