Clustering: finding patterns in the darkness

Machine learning is changing the world and fuelling Industry 4.0. These statistical methods focused on identifying patterns in data to provide an intelligent response to specific requests. Although understanding data tends to require expert knowledge to supervise the decision-making process, some techniques need no supervision. These unsupervised techniques can work blindly but they are based on data similarity. One of the most popular areas in this field is clustering. Clustering groups data to guarantee that the clusters’ elements have a strong similarity while the clusters are distinct among them. This field started with the K-means algorithm, one of the most popular algorithms in machine learning with extensive applications. Currently, there are multiple strategies to deal with the clustering problem. This review introduces some of the classical algorithms, focusing significantly on algorithms based on evolutionary computation, and explains some current applications of clustering to large datasets.

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.