T2RFIS: Type-2 Regression-based Fuzzy Inference System

T2RFIS is a novel simple fuzzy inference system with type-2 fuzzy sets without explicitly defined fuzzy rules based on ridge regression.

This project concerns training fuzzy systems on the basis of ridge regression. These systems use Gaussian type-2 fuzzy sets for the inputs and a linearly parameterized system function to obtain the output. The input fuzzy sets are determined by a multi-objective genetic algorithm with a feature selection method. The multi-criteria objective functions enable the selection of models from the Pareto fronts taking into account the compromise between model accuracy and its simplification.

The package contains an example of using the T2RFIS method to predict automobile fuel consumption in miles per gallon (MPG). The data can be downloaded from: https://archive.ics.uci.edu/ml/datasets/auto+mpg Original data-set contains 398 rows, but the records with missing values have been removed, so we have 392 rows.

Using this method, please cite as:

Wiktorowicz K., 'RFIS: regression-based fuzzy inference system', Neural Computing and Applications, vol. 35, pp. 20299–20317, 2023, DOI: https://doi.org/10.1007/s00521-023-08811-7

Available at:

https://www.researchgate.net/publication/372486432_T2RFIS_type-2_regression-based_fuzzy_inference_system

https://link.springer.com/article/10.1007/s00521-023-08811-7