| Popis: |
This thesis presents the development of a novel fuzzy regression tree algorithm known as Elgasir, which is based on the CHAID regression tree algorithm and Takagi-Sugeno fuzzy inference. The Elgasir Algorithm is applied to crisp regression trees to produce fuzzy regression trees in order to soften sharp decision boundaries inherited in crisp trees. Elgasir generates a fuzzy rule base by applying fuzzy techniques to crisp regression trees using Trapezoidal membership functions. Then Takagi-Sugeno fuzzy inference is used to aggregate the final output from the fuzzy implications. A novel optimization method based on the Artificial Immune Network model (opt-aiNet) is also proposed to optimize the fuzzification of fuzzy regression trees generated by the Elgasir Algorithm. Finally, the Elgasir Algorithm is developed further by proposing a new approach to creating fuzzy regression tree forests based upon the induction of multiple fuzzy regression decision trees from one training sample, where each tree will represent a different view of the data domain. A significant number of experiments were carried out for each of the proposed approaches, using five real-world regression problems from the VCI repository and KEEL repository. The empirical results have shown the effectiveness of using the proposed methods by increasing the prediction accuracy and robustness of fuzzy regression trees. |
