An Improved Two-Phase GAI Particle Swarm Optimization Data Clustering Algorithm
The well-known k-means algorithm that has been successfully applied to many practical clustering problems, suffers from several drawbacks due to its choice of initializations. In order to overcome k-means shortcomings, hybrid algorithms involving evolutionary algorithms are a good option for boosting the clustering performance. In this study, a hybrid two-phase algorithm for data clustering is proposed. In the first phase we utilize the new genetically improved PSO algorithm (GAI-PSO) which combines the standard velocity and position update rules of PSOs with the ideas of selection, mutation and crossover from GAs. The GAI-PSO algorithm searches the solution space to find an optimum initial seed for the next phase. The second phase is a local refining stage utilizing the k-means algorithm which can efficiently converge to the optimum solution.
Ran Chen and Wen-Pei Sung
Q. F. Liu, "An Improved Two-Phase GAI Particle Swarm Optimization Data Clustering Algorithm", Advanced Materials Research, Vols. 490-495, pp. 1431-1435, 2012