A Sequential Ensemble Model for Communicable Disease Forecasting

Background: Ensemble building is a popular method for improving model accuracy for classification problems as well as regression. Objective: In this research work, we propose a sequential ensemble model to predict the number of incidences for communicable diseases like influenza, hand foot and mouth disease (HFMD), and diarrhea and compare it with applied models for prediction. Methods: The weekly dataset of the three diseases, namely, influenza, HFMD, and diarrhea, are collected from the official government site of Hong Kong from the year 2010 to 2018. The data was preprocessed by taking log transformation and z-score transformation. The proposed sequential ensemble model is applied to the processed dataset to predict future occurrences. Results: The result of the proposed ensemble model is compared against standard support vector regression (SVR) using different error metrics such as root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). In the case of all the threedisease datasets, the proposed ensemble model gives better results in comparison to the standard SVR model. Conclusion: The main objective of this research work is to minimize the prediction error; the proposed sequential ensemble model has shown a significant result in terms of prediction errors.