Extreme Learning Machine Method for Dengue Hemorrhagic Fever Outbreak Risk Level Prediction

Abstract

Dengue Hemorrhagic Fever (DHF) is one of the major health problems in Indonesia. With increasing mobility and population density, weather changes, other epidemic factors, the number of dengue fever patients also increases. In order to optimize the prevention of DHF outbreaks, it is important to obtain predictions related to the risk level of DHF outbreak, because each region needs to be treated according to its risk level. The spread of DHF is closely related to weather conditions. Therefore in this study, we apply extreme learning machine (ELM) method to predict the risk of outbreak based on weather condition. We Develop ELM architecture with weather variables as input nodes and risk level of DHF outbreak as the target. We use binary sigmoid activation function and bipolar sigmoid with a number of hidden neurons between 5- 200 nodes. The results show that ELM can predict the level of risk of DHF with the best performance of ELM network using a binary sigmoid activation function with 50 hidden neurons.