Analysis of several decision fusion strategies for clustering validation. Strategy definition, experiments and validation

Abstract

In the unsupervised learning environment, the correct partition of data is not available, making it difficult to evaluate the performance of clustering algorithms. Therefore, one of the biggest challenges in this area is the validation of the results obtained by the algorithms. Amongst the various proposals currently under discussion, one of the most popular approaches is the one based on internal cluster validity indexes (CVIs). Comparative studies of such indexes show that there is no optimal CVI able to cope successfully with all the contexts. The aim of this work is to implement and analyse several decision fusion strategies over the CVIs studied in an extensive comparative work published in the bibliography, motivated by the success achieved by voting strategies in supervised learning. Thus, this experimental work consists of designing and implementing different CVI decision fusion strategies and then evaluating their performance in order to discover which of them are promising and eventually select the best one. Experiments with several strategies showed that the majority of the decision fusion approaches designed cope with the diversity of contexts more effectively than single CVIs.