A genetic algorithm for generating fuzzy classification rules

Fuzzy classification systems based on fuzzy logic are capable of dealing with cognitive uncertainties such as vagueness and ambiguity involved in classification problems. To build a fuzzy classification system, the key is to find an optimal set of fuzzy rules. Machine learning methods such as fuzzy neural networks and fuzzy decision tree induction have been applied to learn fuzzy rules but they may be trapped into local optimal. Based on the principle of natural evolution and global searching, a genetic algorithm is promising in obtaining better results but it is usually less efficient. In this paper, a Fuzzy Genetic Algorithm (FGA) is developed to generate fuzzy classification rules. Several techniques such as multi-value logic coding, composite fitness function, viability check, and rule extraction are used to improve the efficiency and the effectiveness of the algorithm. Two experiments are conducted to demonstrate the performance of FGA and to compare FGA with other machine learning algorithms.