Automatic Generation of Fuzzy Rule-based Models from Data by Genetic Algorithms
Plamen Parvanov Angelov, Richard A. Buswell, Vic I. Hanby, Jonathan A. Wright · 2001
The so-called classical models (which are based on differential equations, energy- and mass-balance principles and neglect qualitative and subjective information) are inadequate or practically difficult to use in many cases [1]. In last decade fuzzy models have been widely used in different fields like economics, biotechnology, civil engineering etc. They have a very important advantage over neural-network-based models in that they are transparent; that they contain expressible knowledge about the object being modelled. Determination of fuzzy rules and membership functions of fuzzy sets, however, is usually based on subjective estimation. In many cases it is a complex and ambiguous process [1].