Swarm intelligence for clustering - A systematic review with new perspectives on data mining

The increase in available data has attracted the interest in clustering approaches as a way of coherently aggregating them and identify patterns in big data. Hence, Swarm Intelligence techniques can outperform standard clustering techniques in some real problems. Indeed, they can replace standard techniques in some cases. The knowledge regarding the problem is not enough to select the best algorithm. It is also necessary to unveil which techniques are relevant in the literature. This paper presents a systematic mapping review on recent investigations of swarm-inspired algorithms to tackle clustering problems. We selected 161 articles from the most important scientific databases, which were published over the last six years. We discuss many aspects, such as the most used fitness functions, validation indexes, encoding schemes, hybrid proposals, frequent applications, among others. We provide an overview of how to apply the swarm methods together with a critical analysis of the current and future perspectives in the field.