Hybrid Harmony Search and Genetic for Fuzzy Classification Systems

In this paper, a method based on Harmony Search Algorithm (HSA) is proposed for pattern classification. One of the important issues in the design of fuzzy classifier if the product of fuzzy if then rules. So that the number of incorrectly classified patterns is minimized. In the HSA-based method, every musician makes a musical note and it can be regarded as a solution vector. The algorithm uses Genetic algorithm based local search to improve the quality of fuzzy classification system. The proposed algorithm is evaluated on a breast cancer data. The results show that the algorithm based on improved genetic is able to produce a fuzzy classifier to detect breast cancer.