Optimization of the Fuzzy Integrators in Ensembles of ANFIS Model for Time Series Prediction: The case of Mackey-Glass

This paper describes the optimization of the fuzzy integrators in Ensembles of ANFIS models for time series prediction, this with emphasis on its application to the prediction of Mackey-Glass time series, so this benchmark time series is used to the test of performance of the proposed ensemble architecture. We used fuzzy systems to integrate the outputs (forecasts) of each of the ANFIS models in the Ensemble. Genetic Algorithms (GAs) were used for the optimization of memberships function parameters of the fuzzy integrators. In the fuzzy integrators, we applied different noise levels. Simulation results show the effectiveness of the proposed approach.