Interval Type-2 Fuzzy Logic System Based on Multi-resolution Analysis

In order to effectively express and deal with the uncertainty of systems, an interval type-2 fuzzy logic system based on multi-resolution analysis was proposed, and a multi-resolution interval type-2 membership function was constructed. In addition, its structure and learning algorithm were given based on scaling function decomposition. The antecedent of the multi-resolution interval type-2 fuzzy system is a multi-resolution membership function, and the consequent is a linear function of inputs. As a result, the multi-resolution interval type-2 fuzzy system can divide the input universe adaptively and optimize system architecture. Finally, a noisy time series was predicted using the multi-resolution interval type-2 fuzzy system. The complexity of the prediction result is small, and the root-mean-square error is 0.105 2.