METODE SIKLIS DAN ADAPTIVE NEURO FUZZY INFERENCE SYSTEM UNTUK PERAMALAN CUACA

Abstract

The erratic of weather changes make weather conditionsunpredictable in the future. Thus, in this study we used a method that could predict the weather conditions in the span of a few months, the method is Cyclical and Adaptive Neuro Fuzzy Inference System (ANFIS) for weather forecasting. The data that used came from BMKG Karangploso, Malang that using four parameters that affect weather conditions, such as temperature, air pressure, humidity, and wind speed. In addition used of ANFIS in this study will also be used Cyclical method for predicting the weather parameter values. The performance of this model can be maximized by using the value of the learning rate 0.3 that produces an accuracy of 76.67%.