Comparative Review of Fuzzy Rules Generation

Fuzzy rules are usually generated by experts in the area, especially for control problems with only a few inputs. With an increasing number of variables, the number of rules is increasing exponentially, which makes more difficult for experts to define the rule set for good system performance. In solving this, researchers have looked into hybrid the fuzzy based to enhance or reduce complexity. We reviewed two Fuzzy Rules Generations, which is constructed based on Fuzzy Neural Network and Fuzzy Particle Swarm Optimization, respectively. The main section which are used for generation are rule base and membership function. This paper describes each method how to tune the membership function and fuzzy rules as the main phase, step by step.