Identifikasi Epidemi Berbasis Sir Menggunakan Jaringan Saraf Tiruan Runge Kutta Multi Layer Perceptron

Abstract

During an epidemic, population could be divided into those who are susceptible to the disease, those who are infected and those who have recovered. These three parts are implied by the variable function t and may fluctuate over time. Multi Layer Perceptron has been used widely to predict dynamical system in certain time duration but it fails to predict accurately in different time duration. To avoid this weakness. Runge Kutta Multi Layer Perceptron has been proposed. Gradient descent technique is used to change weights and bias. Experiments show that Runge Kutta Multi Layer Perceptron predicts the spread of disease based on SIR model better than Multi Layer Perceptron