TS-fuzzy modeling based on ε-insensitive smooth support vector regression

摘要: This paper establishes a connection between Takagi-Sugeno TS fuzzy systems and e-insensitive smooth support vector regression e-SSVR, strategy for solving e-SVR. In previous e-SVR-based models, the form of membership functions is restricted by Mercer condition. The e-SSVR formulation puts no restrictions on kernel. Therefore, proposed e-SSVR-based TS-fuzzy modeling method relaxes restriction functions. By applying reduced kernel technique, number rules without scarifying generalization ability. computational complexity also technique. performance our illustrated extensive experiments comparisons.