A Genetic-Based Neuro-Fuzzy Generator: NEFGEN

This paper is concemed with the design of new generation of intelligent systems. These systems or machines are intelligent if they are able to improve their performance or maintain an acceptable level of performance in the presence of uncertainty. The ability of these systems to examine and modifr their behaviors in a limited sense is usually achieved by using techniques such as knowledge-based systems (KBS), Artificial Neural Networks (Mvs), Fuuy systems (FSs), and Genetic Algorithms (GAS). In thispaper we propose a novel technique called NEFGEN or Neuro-Fuzzy Generator. This Hybrid NeuroFuuy generator is based on the Knowledge Oriented Design (KOD) concept, Cooperative Neuro-Fuuy systems and Genetic Algorithms. A classification through a competitive neural network of data examples of the application to be performed provides eficient inference rules as well as adequate fuu;y partitions of the input/output variable domains. The resulting fuzzy system is then optimized using random techniques and genetic algorithm techniques. NEFGEN is proved to be very eficient in designing poweijkl fuur expert systems (FESs) especially in classification and approximation. It is also shown that NEFGEN performance exceed those of known hybrid neuro-fuuy systems such as ANFIS, NEFPROX, and NEFCLASS.