Naslov
Investigation of an optimal number of clusters by the adaptive EM algorithm

Autori
Novoselac, Vedran

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, znanstveni

Izvornik
Book of Abstracts 17th International Conference on Operational Research KOI 2018 / Arnerić, Josip ; Čeh Časni, Anita - Zagreb : Printed by Fratres d.o.o., 2018, 22-22

Skup
17th International Conference on Operational Research (KOI 2018)

Mjesto i datum
Zadar, Hrvatska, 26.09.2018. - 28.09.2018

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Clustering ; EM ; Gaussian mixture ; Mahalanobis distance ; Chi-square

Sažetak
This paper considers the investigation of an optimal number of clusters for datasets that are modeled as the Gaussian mixture. For that purpose, an adaptive method that is based on the modified Expectation Maximization (EM) algorithm is developed. The modification is conducted within the hidden variable of the standard EM algorithm. Assuming that data are multivariate normally distributed where each component of Gaussian mixture corresponds to one cluster, the modification is provided by utilizing the fact that the Mahalanobis distance of samples follows a Chi-square distribution. Besides, the quantity measure is constructed in order to determine number of clusters. The proposed method is presented in several numerical examples.

Izvorni jezik
Engleski

Znanstvena područja
Matematika, Računarstvo

POVEZANOST RADA