The Study of K-Means Based on Hybrid SA-PSO Algorithm

This paper introduces the relative principium of K-Means algorithm, simulated annealing (SA) algorithm and particle swarm optimization (PSO) algorithm at first. Then, in allusion to the influence of the initial value of the K-Means algorithm on the optimal solution of the algorithm, a hybrid algorithm of K-Means based on SA-PSO is proposed. The new algorithm uses the advantage of jumping out of local minima to improve the performance of the PSO algorithm, with the global optimization, the new algorithm can overcome the shortcoming of the K-Means algorithm which is easy to fall into the local optimal solution. The experimental result shows that the K-Means algorithm based on the hybrid SA-PSO algorithm compared with the PSO algorithm based on the K-Means algorithm has been partially effective increase in Global convergence.