Time series methods have been applied to forecast clinical data, such as daily patient number forecasting for emergency medical centers. However, the application of conventional time series models needs to meet the statistical assumptions, and not all models can be applied in all datasets. Most of the traditional time series models use a single variable for forecasting, but there are many noises involutedly in raw data that are caused by changes in weather conditions and environments for daily patient number forecasting. Time series models that use complicated raw data would reduce the forecasting performance. For solving the above problems, this paper develops a hybrid time series support vector regression (SVR) model based on empirical mode decomposition (EMD), AR (autoregressive) method, and volatility of data. The proposed model considers that EMD can decompose complicated raw data into highly correlations frequency components. Further, the volatility of data measures data change and implies the dataset's power. For the reason, this paper utilizes the data's volatility as an important variable to improve the proposed forecasting model. Then, this study utilizes SVR as a forecasting model that can overcome the limitations of statistical methods (data need to obey some mathematical distribution). In verification, this paper collects daily patient volumes in emergency departments as experimental datasets to evaluate the proposed model. Numerical results indicate that the proposed model outperforms the listing models.

Back