Affiliations: [a] Centro Universitário C. Limpo Paulista, C. L. Paulista, SP, Brazil | [b] Universidade Federal de S. Carlos, S. Carlos, SP, Brazil
Correspondence:
[*]
Corresponding author: Maria do Carmo Nicoletti, Centro Universitário C. Limpo Paulista (UNIFACCAMP), C. L. Paulista, SP, Brazil. E-mail: [email protected],[email protected].
Abstract: A recurring problem in a wide variety of research areas such as pattern recognition, machine learning, data mining and statistics, among others, is characterized as a clustering problem. Such a problem can be described in a simplistic way as: given a set of data (observations, objects, points, etc.), group similar data into clusters (groups). A clustering of a given data set is then characterized as a set of clusters, in which elements belonging to a cluster are similar to each other and elements belonging to distinct clusters are not similar. Clustering algorithms are non-supervised algorithms and, among the many available in the literature, the k-Means, that uses a random initizalization process, can be considered one of the most popular and successful. The performance of the k-Means, however, is highly dependent on a ‘good’ initialization of the k cluster centers (centroids), as well as on the value assigned to the number (k) of clusters the final clustering should have. This paper addresses experiments using five initialization algorithms available in the literature namely, the Method1, the k-Means++, the CCIA, the Maedeh and Suresh and the SPSS algorithms, to empirically evaluate their contribution for improving the k-Means performance.
