An adaptive neuro-fuzzy inference system-based approach to forecast time series of chaotic systems

Abstract

Forecasting (prediction of) time series of chaotic systems is known as one of the most remarkable research areas within the Chaos Theory. As being associated with needs for more effective, efficient and accurate solution approaches, Artificial Intelligence-based techniques are used for designing forecasting systems to achieve the related objectives. In this sense, this study introduces a system, which was designed on an Adaptive Neuro-Fuzzy Inference System (ANFIS) approach. As a result of learning – reasoning infrastructure ensured by the combination of Artificial Neural Networks and Fuzzy Logic techniques, an alternative solution-based study on forecasting chaotic time series is provided for the literature.