FuzzyRULES: A fuzzy rule induction algorithm for mining classification knowledge
Ali Afify · 2009
Recently, the field of data mining, or knowledge discovery in databases, has attracted considerable attention from both academia and industry. Among types of knowledge to be discovered, classification knowledge is widely explored in engineering applications. A variety of methods exist for learning classification knowledge using crisp sets. This paper presents a new fuzzy rule learner called FuzzyRULES (for fuzzy rule extraction system) that is based on fuzzy sets. The use of fuzzy sets not only provides a powerful, flexible approach to deal with vagueness and uncertainty, but also increases the expressive power and comprehensibility of the learning algorithm. Experimental results show that FuzzyRULES induces highly accurate and comprehensible rules.