A hybrid time-series model based on EMD-feature selection and Random Forest method for medical data forecasting

• Main Authors: TAN, KUO-YEN, 譚國彥
• Other Authors: WEI, LIANG-YING
• Format: Others
• Language: zh-TW
• Published: 2018
• Online Access: http://ndltd.ncl.edu.tw/handle/2f8b8u

碩士 === 元培醫事科技大學 === 資訊管理系數位創新管理碩士班 === 106 === It is very important for hospital managers to allocate emergency department (ED) resources efficiently. Forecasting is a vital activity that instructs decision makers, in related research fields, such as industrial scientific planning, economic, and healthcare. Scientists have applied time series methods to daily patient number forecasting at ED. Traditional time series models usually use single variable for forecasting, but noises caused by weather conditions change and environment factors would be included in raw data. Low forecasting performance would be generated because of using complicated raw data in time series models. Further, traditional time series models can not be utilized in all datasets because statistics models need meet statistical assumptions. Multi-attribute data will usually produce high-dimensional data and increase the computational complexity in datamining procedure. For overcoming these drawbacks above, this study proposes a hybrid time series random-forest model based on AR (autogressive) empirical mode decomposition (EMD). Proposed model utilizes EMD to decompose complicated raw data into correlations frequency components, and uses feature section method to reduce high-dimensional input data generated by EMD. Then, this study combines random forest method that can surmount the limitations of statistical methods (data need to obey some mathematical distribution) to forecast daily patient volumes. In order to verification, daily patient volumes in emergency are collected as experimental datasets to evaluate proposed model. Experimental results illustrate that proposed surpasses the listing models.