Optimal ANFIS Model for Forecasting System Using Different FIS

Abstract

Adaptive Network Based Fuzzy Inference System (ANFIS) using time series analize is one of intelligent systems that can be used to predict with good accuracy in all fields like in meteorology. However, some research about forecasting has less emphasis on the structure of the FIS ANFIS. Thus, in this paper, the optimization of the ANFIS model for predicting maritime weather is carried out by analyzing the appropriate initialization determinations of the three fuzzy Inference structures ANFIS which includes FIS structure 1 (grid partition), FIS structure 2 (subtractive clustering) and FIS structure 3 (fuzzy c-means clustering). In this paper, the variable input used are two hours (t-2) and one hour (t-1) before, and data at that time (t), and the output of this system is the prediction of next hour, six hours, twelve hours and next day of variable ocean currents velocity (cm/s) and wave height (m) using the three FIS ANFIS approaches. Based on the smallest goal error (RMSE and MSE) of the three FIS ANFIS approaches used to predict the ocean currents speed (velocity) and wave height, the model is best generated by subtractive clustering. It can be seen that subtractive clustering produces the smallest RMSE and MSE error values of other FIS structure.