Comprehensive analysis of a new fuzzy rule interpolation method

The first published result in fuzzy rule interpolation was the alpha-cut ba sed fuzzy rule interpolation, termed as KH fuzzy rule interpolation, origin ally devoted for complexity reduction. Some deficiencies of this method was presented later such as subnormal conclusion for certain configuration of the involved fuzzy sets. However, since that several conceptually different fuzzy rule interpolation techniques were proposed, none of those algorithm s has such a low computational complexity than the original one. Recently, a modified version of the KH approach has been presented [1], which elimina tes the subnormality problem while at the same time intending to maintain t he advantageous computational properties of the original method. This paper presents a comprehensive analysis of the new method, which includes detail ed comparison with the original KH fuzzy rule interpolation method concerni ng the explicit functions of the methods, preservation of piecewise lineari ty, and stability. The fuzziness of the conclusion with respect to the fuzz iness of the observation is also investigated in comparison with several in terpolation techniques, All these comparisons shows that the new method pre serves the advantageous properties of the KW method and alleviates its most significant disadvantage, the problem of subnormality.