Hybridization of Support Vector Regression and Firefly Algorithm for Diarrhoeal Outpatient Visits Forecasting

Accurate and reliable forecasts of diarrhoeal outpatient visits are necessary for the health authorities to ensure the appropriate action for the control of the outbreak. In this study, a novel forecasting model based on hybridization the Firefly Algorithm (FA) and Support Vector Regression (SVR) has been proposed to forecast the diarrhoeal outpatient visits in Shanghai. The performance of SVR models depends upon the appropriate choice of SVR parameters. In this study, FA has been employed for determining the parameters. The rainfall, temperature, relative humidity and diarrhoeal outpatient visits have been considered as input variables. Time series of diarrhoeal outpatient visits of children and adult has been obtained for a period of January 2006 to December 2011. Further, the rainfall, relative humidity and temperature data have been obtained from meteorological records. The performance of the proposed SVR-FA model has been compared with Multivariable Linear Regression (MRL) method, Artificial Neural Networks (ANNs) and also with SVR. The results indicate that the proposed model performs best based on two error measures, namely mean squared error (RMSE) and mean absolute percent error (MAPE).