Title :
Evolving fuzzy-madel-based on c-regression clustering
Author :
Skrjanc, Igor ; Dovzan, Dejan ; Gomide, Fernando
Author_Institution :
Laboratory of Modelling, Simulation and Control Faculty of Electrical Engineering, University of Ljubljana Tržaška 25, SI-1000 Ljubljana, Slovenia
Abstract :
In this paper a new approach to data stream evolving fuzzy model identification is given. The structure of the model is given in the form of Takagi-Sugeno and the partitioning of the input-output space is obtained using a fuzzy c-regression clustering method and the approach also involves the evolving properties. The method is given in a recursive form. The proposed approach is shown with two simple examples of nonlinear system approximation and nonlinear dynamical system modelling.
Keywords :
Clustering algorithms; Clustering methods; Computational modeling; Data models; Partitioning algorithms; Prototypes; Vectors; Evolving fuzzy model identification; Fuzzy clustering; Stream data;
Conference_Titel :
Evolving and Adaptive Intelligent Systems (EAIS), 2014 IEEE Conference on
Conference_Location :
Linz, Austria
DOI :
10.1109/EAIS.2014.6867481
