Research on Fuzzy C Switching Regression Model with Generalized Improved Fuzzy Partitions

By introducing a novel membership constraint function, a new algorithm called fuzzy c-means switching regression model with generalized improved fuzzy partitions (GIFP-FCRM) is proposed. This algorithm seems less sensitive to noise and outliers than the classical fuzzy C switching regression model (FCRM), and provides a generalized model with the fuzziness index m for the fuzzy C switching regression model with improved fuzzy partitions (IFP-FCRM). Furthermore, with fuzzy parameter α, the classical FCRM and IFP-FCRM can be taken as two special cases of the proposed algorithm. Several experimental results are presented to demonstrate its advantage over FCRM in both noise insensitivity and robustness capability.