EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Comparison of Initialization Strategies for EM in High-Dimensional Multivariate Diagonal Gaussian Mixture Models

Ewa Radwan, Mateusz Kania, Karolina Widzisz, Joanna Zyla, Agnieszka Szczęsna, Andrzej Polański

Applied Sciences · 29.05.2026 · 16 (11) · 5427

DOI: 10.3390/app16115427 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 29.05.2026. Verfasst von Ewa Radwan und 5 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Silesian University of Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Expectation Maximization (EM) iterations for Gaussian mixture models (GMMs) are highly sensitive to initial parameters, which calls for developing robust initialization methods. For multidimensional GMMs, the problem is even more severe than for univariate GMMs because of the larger number of parameters. For univariate or low-dimensional GMMs, several studies on their initialization have appeared in the literature, whereas research on initializing multivariate, high-dimensional GMMs remains limited. In this study, we compare several initializations for Multivariate Diagonal Gaussian Mixture Models (MDGMMs). In our study, we have included methods already used in the literature for initializing MDGMMs: Hierarchical Clustering, K-means, and random initialization. We have also used a new method, namely, Ensemble Clustering. A review of the existing literature suggests that Ensemble Clustering has not been used previously as an initialization strategy for MDGMM. Several metrics were used to evaluate the clustering quality. Our study demonstrates that Ensemble Clustering, while computationally intensive, is competitive with other methods for initializing MDGMMs.

Förderung

  • Silesian University of Technology

Zitieren

APA

Radwan, E., Kania, M., Widzisz, K., Zyla, J., Szczęsna, A., & Polański, A. (2026). Comparison of Initialization Strategies for EM in High-Dimensional Multivariate Diagonal Gaussian Mixture Models. Applied Sciences, 16(11), 5427. https://doi.org/10.3390/app16115427

Vancouver

Radwan E, Kania M, Widzisz K, Zyla J, Szczęsna A, Polański A. Comparison of Initialization Strategies for EM in High-Dimensional Multivariate Diagonal Gaussian Mixture Models. Applied Sciences. 2026;16(11):5427. doi:10.3390/app16115427

BibTeX
@article{Radwan2026,
  author = {Radwan, Ewa and Kania, Mateusz and Widzisz, Karolina and Zyla, Joanna and Szczęsna, Agnieszka and Polański, Andrzej},
  title = {Comparison of Initialization Strategies for EM in High-Dimensional Multivariate Diagonal Gaussian Mixture Models},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {11},
  pages = {5427},
  doi = {10.3390/app16115427}
}
Kostenlos starten →