Application of neural network to simulate the behavior of hospitalizations and their costs under the effects of various polluting gases in the city of São Paulo

Miranda, Amanda Carvalho; Santana, José Carlos Curvelo; Yamamura, Charles Lincoln Kenji; Rosa, Jorge Marcos; Tambourgi, Elias Basile; Ho, Linda Lee; Berssaneti, Fernando Tobal

doi:10.1007/s11869-021-01077-9

Cited by 7 publications

(6 citation statements)

References 41 publications

(66 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to Seo et al (2022), by using data from multiple monitoring stations, the error associated with the ANN model can be lowered [ 79 ]. The previous studies conducted in São Paulo highlighted the great variability among the data, which may compromise the ability of the model to estimate the most extreme values [ 49 , 50 ]. In this work, the database was split into two seasons with specific meteorological characteristics (Models II and III) and proved to be an efficient way to deal with extreme values, reducing the MAPE to 11% (see Figure 8 ).…”

Section: Discussionmentioning

confidence: 99%

“…The seasonality behind all considered variables is widely described, with increases in pollutant concentrations and mortality during the dry season (from April to September) and reductions in the rainy season (from October to March) [ 53 ]. This characteristic hampers the neural networks from accurately estimating the highest and lowest values, as detected by Araujo et al [ 49 ] and Miranda et al [ 50 ]. For this reason, in this study, three models were developed.…”

Section: Methodsmentioning

confidence: 99%

“…The comparison between the classical generalized linear model (GLM) and the artificial neural network in São Paulo revealed that the ANN shows better results when modeling the daily hospital admissions due to PM 10 exposure and meteorological conditions [ 49 ]. In a multipollutant analysis, Miranda et al [ 50 ] considered the monthly mean concentration of six air pollutants (PM 10 , PM 2.5 , O 3 , CO, SO 2 , and NO 2 ) to estimate hospitalizations for respiratory diseases. The best ANN found by the authors was able to estimate 85.5% of the experimental data, and the percentage errors (from 2% to 25%) were considered low [ 50 ].…”

Section: Introductionmentioning

confidence: 99%

“…In a multipollutant analysis, Miranda et al [ 50 ] considered the monthly mean concentration of six air pollutants (PM 10 , PM 2.5 , O 3 , CO, SO 2 , and NO 2 ) to estimate hospitalizations for respiratory diseases. The best ANN found by the authors was able to estimate 85.5% of the experimental data, and the percentage errors (from 2% to 25%) were considered low [ 50 ]. Despite the good result, the study did not consider meteorological variables.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Multi-Pollutant and Meteorological Analysis of Cardiorespiratory Mortality among the Elderly in São Paulo, Brazil—An Artificial Neural Networks Approach

Leirião

Oliveira

Martins

et al. 2023

IJERPH

View full text Add to dashboard Cite

Traditionally, studies that associate air pollution with health effects relate individual pollutants to outcomes such as mortality or hospital admissions. However, models capable of analyzing the effects resulting from the atmosphere mixture are demanded. In this study, multilayer perceptron neural networks were evaluated to associate PM10, NO2, and SO2 concentrations, temperature, wind speed, and relative air humidity with cardiorespiratory mortality among the elderly in São Paulo, Brazil. Daily data from 2007 to 2019 were considered and different numbers of neurons on the hidden layer, algorithms, and a combination of activation functions were tested. The best-fitted artificial neural network (ANN) resulted in a MAPE equal to 13.46%. When individual season data were analyzed, the MAPE decreased to 11%. The most influential variables in cardiorespiratory mortality among the elderly were PM10 and NO2 concentrations. The relative humidity variable is more important during the dry season, and temperature is more important during the rainy season. The models were not subjected to the multicollinearity issue as with classical regression models. The use of ANNs to relate air quality to health outcomes is still very incipient, and this work highlights that it is a powerful tool that should be further explored.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Multi-Pollutant and Meteorological Analysis of Cardiorespiratory Mortality among the Elderly in São Paulo, Brazil—An Artificial Neural Networks Approach

Leirião

Oliveira

Martins

et al. 2023

IJERPH

View full text Add to dashboard Cite

show abstract

“…Air pollution does not only have negative effects on the climate, ecosystems and human health, but more and more often is associated with financial and economic effects for entire countries or regions [ 1 , 2 ].…”

Section: Introductionmentioning

confidence: 99%

Particulate Matter Concentration in Selected Facilities as an Indicator of Exposure to Their Service Activities

Rogula-Kopiec

Rogula–Kozłowska

Majewski

2022

IJERPH

View full text Add to dashboard Cite

In recent years, the correlation between the concentration of pollutants in the atmosphere and inside buildings has been reported as high. The air inside living quarters and public utility buildings or the interiors of public transport vehicles, as well as the relationship between the internal and external sources of particulate matter (PM) and gaseous pollutants, have underwent sufficient research. On the other hand, non-production rooms, i.e., offices, restaurants, beauty salons, etc. remain very poorly recognized in this respect. For the above reasons, the aim of this work is to determine the difference in the total dust (TSP) and respirable PM (PM4) concentrations in selected rooms, i.e., offices and beauty centers, in relation to their outdoor concentrations. They were measured at six locations in accordance with the standard for the conditions at workplaces by means of PM aspirators. Indoor concentrations of TSP and PM4 were much higher than those in the external surroundings of the facilities. There were no significant relationships between the TSP and PM4 concentrations inside and outside tested rooms. Although the characteristic of the internal PM essentially depends on the characteristics of the external PM migrating to the interior of the premises, considering some types of non-production premises, internal emissions fundamentally changed the characteristics of PM.

show abstract

A neuro-fuzzy model to predict respiratory disease hospitalizations arising from the effects of traffic-related air pollution in São Paulo

Santana,

Miranda,

Rosa

et al. 2024

Clean Techn Environ Policy

View full text Add to dashboard Cite

Application of neural network to simulate the behavior of hospitalizations and their costs under the effects of various polluting gases in the city of São Paulo

Cited by 7 publications

References 41 publications

A Multi-Pollutant and Meteorological Analysis of Cardiorespiratory Mortality among the Elderly in São Paulo, Brazil—An Artificial Neural Networks Approach

A Multi-Pollutant and Meteorological Analysis of Cardiorespiratory Mortality among the Elderly in São Paulo, Brazil—An Artificial Neural Networks Approach

Particulate Matter Concentration in Selected Facilities as an Indicator of Exposure to Their Service Activities

A neuro-fuzzy model to predict respiratory disease hospitalizations arising from the effects of traffic-related air pollution in São Paulo

Contact Info

Product

Resources

About