Cluster ensembles are deemed to be better than single clustering algorithms for discovering complex or noisy structures in data. We consider different heuristics to introduce diversity in cluster ensembles and study their individual and combined effect on the ensemble accuracy. Our experiments with three artificial and three real data sets, and 12 ensemble types, showed that the most successful...

In this paper we propose a clustering process which uses a multi-objective evolution to select a set of diverse clusterings. The selected clusterings are then combined using a consensus method. This approach is compared to a clustering process where no selection is applied. We show that careful selection of input ensemble members can improve the overall quality of the final clustering. Our algo...

This paper describes a novel approach to profiling phishing emails based on the combination of multiple independent clusterings of the email documents. Each clustering is motivated by a natural representation of the emails. A data set of 2048 phishing emails provided by a major Australian financial institution was pre-processed to extract features describing the textual content, hyperlinks and ...

Cluster ensembles organically integrate individual component methods which may utilise different parameter settings and features, and which may themselves be generated on the basis of different representations and learning mechanisms. Such a technique offers an effective means for aggregating multiple clustering results in order to improve the overall clustering accuracy and robustness. Many to...

Clustering ensemble mainly relies on the pairwise similarity to capture the consensus function. However, it usually considers each base clustering independently, and treats the similarity measure roughly with either 0 or 1. To address these two issues, we propose a coupled framework of clustering ensembles CCE, and exemplify it with the coupled version CCSPA for CSPA. Experiments demonstrate th...

This paper discusses one method of clustering a high dimensional dataset using dimensionality reduction and context dependency measures (CDM). First, the dataset is partitioned into a predefined number of clusters using CDM. Then, context dependency measures are combined with several dimensionality reduction techniques and for each choice the data set is clustered again. The results are combine...

In the past decade many new methods were proposed for creating diverse classifiers due to combination. In this paper a new method for constructing an ensemble is proposed which uses clustering technique to generate perturbation in training datasets. Main presumption of this method is that the clustering algorithm used can find the natural groups of data in feature space. During testing, the cla...

This research introduces a new strategy in cluster ensemble selection by using Independency and Diversity metrics. In recent years, Diversity and Quality, which are two metrics in evaluation procedure, have been used for selecting basic clustering results in the cluster ensemble selection. Although quality can improve the final results in cluster ensemble, it cannot control the procedures of ge...

Hierarchical clustering algorithms are widely used in many fields of investigation. They provide a hierarchy of partitions of the same dataset. However, in many practical problems, the selection of a representative level (partition) in the hierarchy is needed. The classical approach to do so is by using a cluster validity index to select the best partition according to the criterion imposed by ...

After more than five decades, a huge number of models and algorithms have been developed for data clustering. While most attention has been devoted to data types, algorithmic features, and application targets, in the last years there has also been an increasing interest in developing advanced dataclustering tools. In this respect, projective clustering and clustering ensembles represent two of ...