Search

Air pollution levels exceeding the recommended limit can be the main cause of illnesses that affect human health, mainly diseases of the respiratory system. Consequently, this high exposure can impact public health management, given the increase in hospital admissions. One of the most influential air pollution parameters related to respiratory diseases is particulate matter (PM) concentrations. Thus, this paper proposes to estimate hospital admissions due to respiratory diseases caused by PM concentration with an aerodynamic diameter less than 10 μ m (PM 10 ), using artificial neural networks. Three hybrid neural network models are developed by combining two architectures denoted unorganized machines: extreme learning machines and echo state networks. These models also comprise extension strategies that seek to improve the generalization capability and the variation in the nonlinear outputs. Case studies explore three cities' datasets from São Paulo state, Brazil: Cubatão, Campinas, and São Paulo, to assess the quality of the hospital admissions estimations obtained by applying the proposed models. Results demonstrate that the hybrid models outperform the previously developed standard approaches in several scenarios. An overall analysis shows that the hybrid models can be a suitable strategy considering the instance particularities, especially in large datasets. [ABSTRACT FROM AUTHOR]

The particulate matter PM 10 concentrations have been impacting hospital admissions due to respiratory diseases. The air pollution studies seek to understand how this pollutant affects the health system. Since prediction involves several variables, any disparity causes a disturbance in the overall system, increasing the difficulty of the models' development. Due to the complex nonlinear behavior of the problem and their influencing factors, Artificial Neural Networks are attractive approaches for solving estimations problems. This paper explores two neural network architectures denoted unorganized machines: the echo state networks and the extreme learning machines. Beyond the standard forms, models variations are also proposed: the regularization parameter (RP) to increase the generalization capability, and the Volterra filter to explore nonlinear patterns of the hidden layers. To evaluate the proposed models' performance for the hospital admissions estimation by respiratory diseases, three cities of São Paulo state, Brazil: Cubatão, Campinas and São Paulo, are investigated. Numerical results show the standard models' superior performance for most scenarios. Nevertheless, considering divergent intensity in hospital admissions, the RP models present the best results in terms of data dispersion. Finally, an overall analysis highlights the models' efficiency to assist the hospital admissions management during high air pollution episodes. [ABSTRACT FROM AUTHOR]