Accurate partitional clustering algorithm based on immunized PSO

Hybrid evolutionary algorithms are created by suitably combining the good features of two parent evolutionary algorithms, normally provide better solutions than the individual ones. In this paper we have formulated the partitional clustering as an optimization problem and solved it by a newly developed hybrid evolutionary algorithm Immunized PSO. Simulation studies on four benchmark UCI datasets demonstrate the superior performance of the proposed algorithm compared to the standard K-means, Correlation, PSO and CLONAL clustering algorithms in terms of percentage of accuracy, convergence characteristics, stability and computational efficiency achieved over fifty independent runs.