OPTIMIZATION OF ENSEMBLE NEURAL NETWORKS WITH TYPE-2 FUZZY INTEGRATION OF RESPONSES FOR THE DOW JONES TIME SERIES PREDICTION

This paper describes an optimization method based on genetic algorithms for designing ensemble neural networks with fuzzy response aggregation to forecast complex time series. The time series that was considered in this paper, to compare the hybrid approach with traditional methods, is the Dow Jones data, and the results are presented for the optimization of the structure of the ensemble neural network with type-1 and type-2 fuzzy response integration. Simulation results show that the ensemble approach produces 99% prediction accuracy for the Dow Jones time series and that using type-2 fuzzy logic improves the performance of the predictor.