A Multiclustering Evolutionary Hyperrectangle-Based Algorithm

Abstract

Clustering is a grouping technique that has long been used to relate data homogeneously. With the huge growth of complex datasets from different sources in the last decade, new paradigms have emerged. Multiclustering is a new concept within clustering that attempts to simultaneously generate multiple clusters that are bound to be different from each other, allowing to analyze and discover hidden patterns in the dataset compared to single clustering methods. This paper presents a hybrid methodology based on an evolutionary approach with the concepts of hyperrectangle for multiclustering, called MultiCHCClust. The algorithm is applied in a post-processing stage and it improves the results obtained for a clustering algorithm with respect to the partitioning of the dataset and the optimization of the number of partitions, achieving a high degree of compactness and separation of the partitioned dataset as can be observed in a complete experimental study.