A Novel Hybrid Approach for Diarrhea Prediction

Accurate and reliable forecasts of diarrhea incidences are necessary for the health authorities to ensure the appropriate action for the control of the outbreak. In this paper, a novel hybrid model known as EEMD-GRNN is proposed to forecast the diarrhea incidences. The proposed approach first uses Ensemble Empirical Mode Decomposition (EEMD), which can adaptively decompose the complicated raw time series data into a finite set of intrinsic mode functions (IMFs) and a residue, which have simpler frequency components and higher correlations. The IMF components and residue are than modeled and forecasted using GRNN and the final prediction result can be obtained by these prediction results using the principle of ensemble. The proposed hybrid method is examined by predicting the monthly diarrhea cases number of children and adult located in Shanghai of China. The experimental results indicate that the proposed EEMD-GRNN model provides more accurate forecasts compared to the other ARIMA, single GRNN models and hybrid model (EMD-GRNN). Overall, the proposed approach was effective in improving the prediction accuracy. Keywords—Diarrhea prediction; Ensemble empirical mode decomposition; Generalized regression neural network; Hybrid approach