Comparação entre Redes Neurais Artificiais para Avaliação do Impacto do MP10 na Saúde Humana

• João Luiz M. Meyer UTFPR
• Hugo Siqueira Valadares UTFPR
• Thiago Antonini Alves UTFPR
• Yara de Souza Tadano UTFPR

DOI: https://doi.org/10.5753/sbcas.2021.16109

Abstract

The high emission of air pollutants in large urban centers causes several harms for population health. In this work, the proposal was to estimate the number of hospital admissions for respiratory diseases due to the concentration of particulate matter with an aerodynamic diameter less than or equal to 10 micrometers (PM10) using two Artificial Neural Networks, Multilayer Perceptron (MLP) and Extreme Learning Machines (ELM). The considered models' inputs are PM10 concentration and meteorological variables. The computational results showed that the MLP was able to achieve better performances.

References

Araujo, L. N. et al. (2020) Ensemble method based on Artificial Neural Networks to estimate air pollution health risks. Environmental Modelling and Software, vol. 123, 104567.

CETESB - Companhia Ambiental do Estado de São Paulo (2021) https://cetesb.sp.gov.br/ar/poluentes/, março.

CETESB - Companhia Ambiental do Estado de São Paulo (2018) https://cetesb.sp.gov.br/ar/qualar/, outubro.

DataSUS - Departamento de Informática do Sistema Único de Saúde (2018) http://www2.datasus.gov.br/DATASUS/%20index.php?area=02, dezembro.

Freitas, A. M. e Solci, M. C. (2009) Caracterização do MP10 e MP2,5 e distribuição por tamanho de cloreto, nitrato e sulfato em atmosfera urbana e rural de Londrina. Química Nova, vol. 32, páginas 1750-1754.

Haykin, S. (2015), Neural Networks and Learning Machines, Prentice Hall, 3rd edition.

IBGE - Instituto Brasileiro de Geografia e Estatística (2019) https://www.ibge.gov.br/estatisticas-novoportal/sociais/populacao/9103-estimativas-de-populacao.html?1/4&t1/4resultados, julho.

OMS - Organização Mundial da Saúde (2020) “Air Pollution”, https://www.who.int/health-topics/air-pollution#tab=tab_1, maio.

Python (2019) https://phyton.org, agosto.

Polezer et al. (2018) Assessing the impact of PM 2.5 on respiratory disease using artificial neural networks. Environmental Pollution, vol. 235, pages 394-403.

Silva, I. D. et al. (2010), Redes Neurais Artificiais para Engenharia e Ciências Aplicadas, Artliber, 1ª edição.

Tadano, Y. S. et al. (2021) Dynamic model to predict the association between air quality, COVID-19 cases, and level of lockdown. Environmental Pollution, vol. 268, 115920.

Tadano, Y. S. et al. (2012) “Methodology to assess air pollution impact on human health using the Generalized Linear Model with Poisson regression”, In: Air Pollution – Monitoring, Modelling and Health, Edited by D. M. Khare, Intech, England.

Tadano, Y. S. et al. (2016) Unorganized machines to predict hospital admissions for respiratory diseases. 2016 IEEE Latin American Conference on Computational Intelligence (LA-CCI).