Fast Nondominated Sorting Genetic Algorithm For Multi-Objective Clustering Ensemble

Abstract

Clustering ensemble is to integrate the results of multiple base clustering by consensus function, which can improve the robustness, stability, and accuracy of the clustering algorithm. The existing clustering ensemble methods are basically to design a single consensus algorithm for integration. This paper proposes a fast nondominated sorting genetic algorithm for multi-objective clustering ensemble (NSGAMCE). In this model, two consensus functions are designed to act on the original data and the base clustering results respectively. Secondly, the nondominated sorting genetic algorithm II (NSGA-II) is used to solve the model, and the gene mutation strategy is changed to improve the convergence speed. Then, according to the solving process of the model, the corresponding clustering ensemble algorithm is designed. Finally, the standard data set and the comparison algorithm are used to carry out experiments. The experimental results show that the clustering ensemble algorithm has good performance.