Abstract:

The fuzzy C-means algorithm is widely used due to its simplicity and speediness. However, it is sensitive to  the initial value and easy to fall into local optimum. We propose a new fuzzy clustering based on niching firefly. The algorithm utilizes the chaotic sequence to initialize the firefly population so as to obtain the initial population. The introduction of random inertia weight not only decreases the number of iterations, but also balances the global search ability and the local search ability of the algorithm. By implementing the niche in the process of the iteration algorithm, the diversity of population is increased and the algorithm’s speed is accelerated. Simulation results show that the proposed algorithm can suppress precociousness effectively and ensure population diversity. It can also avoid falling into the local optimum and achieve good clustering performance.

Key words: cube mapping, random inertia weight, firefly, niche technology