Consensus Clustering Based on Particle Swarm Optimization Algorithm

Clustering is an important data mining task and has been explored extensively by a number of researchers for different application areas. The clustering ensembles combine multiple partitions generated by different clustering algorithms into a single clustering solution. Clustering ensembles have emerged as a prominent method for improving robustness, stability and accuracy of clustering solutions. So far, many contributions have been made to find consensus clustering. One of the major problems in clustering ensembles is the consensus function. In this paper, the Particle Swarm Optimization algorithm (PSO) is proposed to solve the consensus clustering problem. We find that the particle swarm clustering algorithm is efficient for this problem. An empirical study compares the accuracy of our proposed algorithms with other consensus clustering methods including voting on five data sets. The experimental results show that the PSO consensus clustering method produces clustering´s that are as good as, and often better than, these other methods.