Iterative Learning of Multiple Univariate Zero-Order T-S Fuzzy Systems

This paper proposes an iterative learning approach to learn a fuzzy system composed of a sum of multiple univariate zero-order Takagi-Sugeno (T-S) fuzzy systems. The learning algorithm is based on the backfitting algorithm, and new fuzzy rules are iteratively added based on a novelty detection criterion, which gives the novelty degree of a new data by a value between zero and one, allowing an easier rule creation threshold's definition. In order to validate the performance of the proposed approach, 10 benchmark data sets are used to compare the proposed approach with two well-known state-of-the-art methods, the Extreme Learning Machine (ELM), and the Support Vector Regression (SVR), and with the GAM-ZOTS approach, which model is similar to the proposed approach. From the results, it is concluded that the proposed approach outperforms ELM, SVR and GAM-ZOTS in almost all data sets.