Forecasting Epidemiological Time Series Based on Decomposition and Optimization Approaches

Abstract

Epidemiological time series forecasting plays an important role in health public system, since it allows managers to develop strategic planning to avoid possible epidemics. In this aspect, a hybrid approach is developed to forecast confirmed cases of megingitis in the Para, Parana and Santa Catarina states, Brazil. In this case, ensemble empirical mode decomposition (EEMD) is applied to decompose the original signal, quantile random forests (QRF) is adopted to forecast each component obtained in decomposition stage and multi-objective optimization (MOO) is used to reconstruct the final forecasting. To assess the performance of adopted methodology, comparisons are conducted with approach that considers to reconstruct the signal by simple sum (EEMD-QRF) and QRF without decomposition. In this context criteria such as mean squared error, symmetric mean absolute percentage error and coefficient of determination as well as statistical tests are adopted. As results, EEMD-QRF-MOO reached lower errors and better coefficient of determination in most of the cases. Indeed, the EEMD-QRF-MOO and EEMDQRF squared errors are statistical equals, and lower than QRF squared errors. With these results it is conclude that using decomposition technique combined with machine learning models and optimization approach can be adopted to enhance the model performance, whose results may be used to perform accurate forecasting. Keywords—Decomposition, ensemble, time series, meningitis, multi-objective optimization.