Clustering Algorithm Based on Fruit Fly Optimization

摘要

The swarm intelligence optimization algorithms have been widely applied in the fields of clustering analysis, such as ant colony algorithm, artificial immune algorithm and so on. Inspired by the idea of fruit fly optimization algorithms, this paper presents Fruit Fly Optimization Clustering Algorithm (FOCA) based on fruit fly optimization. The algorithm extends the space which fruit fly from two-dimension to three, in order to find the global optimum in each iteration. Besides, for the purpose of getting the optimize clusters centers, each fruit fly flies step by step, and every flight is a stochastic search in its own region. Compared with the other clustering algorithms of swarm intelligence, the proposed algorithm is simpler and with fewer parameters. The experimental results demonstrate that our algorithm outperforms some of state-of-the-art algorithms regarding to the accuracy and convergence time.