Model Selection in Adaptive Neuro Fuzzy Inference System (ANFIS) by using Inference of R2 Incremental for Time Series Forecasting

The aim of this paper is to propose a procedure for model selection in Adaptive Neuro-Fuzzy Inference System (ANFIS) for time series forecasting. In this paper, we focus on the model selection based on statistical inference of R2 incremental. The selecting model is conducted by evaluating the inputs, number of membership functions and rules in architecture of ANFIS until the contribution of R2 incremental was not significant. We use simulation data as a case study. The results show that statistical inference of R2 incremental is an effective procedure for model selection in ANFIS for time series forecasting.