Abstract: Clustering remains an active field of different domain research currently. No single algorithm is identified, which can group every real world datasets resourcefully and without error. Our proposed technique be different from the classical ant system in the sense that here the pheromone trail are simplified in behaviour. The capability of Multi Swarm Optimization (MSO), heuristic technique for search of optimal solutions based on the perception of swarm, to powerfully face classification of multiclass database instances. it is evident that the proposed method outperforms other methods compared. The experimental result show the proposed technique is efficient.

Keywords: Ant Colony Clustering Algorithm, Swarm Intelligence Algorithm, multi Swarm Optimization.