PERAMALAN INFLASI DENGAN METODE PARTICLE SWARM OPTIMIZATION – EXTREME LEARNING MACHINE

Abstract

The Extreme Learning Machine (ELM) method is a learning method on an artificial neural network that is used to solve non-linear problems. In this article, the Particle Swarm Optimization (PSO) method is combined with the Extreme Learning Machine (ELM) method to determine the number of neurons in the hidden layer, so that the results obtained are quite accurate and more efficient in terms of time. Furthermore, the PSO-ELM method was applied to inflation data in Indonesia, and the results showed that the Roots Mean Square Error (RMSE) value in the training process was 0.005487935, and the RMSE value in the testing process was 0.4124935. These results indicate that the PSO-ELM method is suitable for forecasting inflation in Indonesia.