Prediction of chaotic time series based on hierarchical fuzzy-clustering

The paper introduces a new method for fuzzy modeling based on a hierarchical fuzzy-clustering scheme. The method consists of a sequence of steps aiming at developing a Takagi-Sugeno (TS) fuzzy model of optimal structure. The premise parameters' identification consists of two steps: Start from an initial fuzzy partition of input space by a nearest-neighbor clustering method to get the number of rules and the initial clustering center; then premise parameters are further processed using a fuzzy C-means algorithm (FCM). The conclusion parameters are identified by the weighted least square method and further optimized by selective recursive least square method. To illustrate the performance of the proposed method, simulations on chaotic Mackey-Glass time series prediction are performed. The results show that the chaotic Mackey-Glass time series are accurately predicted, which demonstrates the effectiveness of this method.