Comparison of Various Definitions of Proximity in Mixture Estimation

0461565 - ÚTIA 2017 RIV PT eng C - Konferenční příspěvek (zahraniční konf.)
Nagy, Ivan - Suzdaleva, Evgenia - Pecherková, Pavla
Comparison of Various Definitions of Proximity in Mixture Estimation.
Proceedings of the 13th International Conference on Informatics in Control, Automation and Robotics (ICINCO 2016). Setubal: SCITEPRESS, 2016, s. 527-534. ISBN 978-989-758-198-4.
[International Conference on Informatics in Control, Automation and Robotics /13./ (ICINCO 2016). Lisbon (PT), 29.07.2016-31.07.2016]
Grant CEP: GA ČR(CZ) GA15-03564S
Institucionální podpora: RVO:67985556
Klíčová slova: classification * recursive mixture estimation * proximity * Bayesian methods * mixture based clustering
Kód oboru RIV: BB - Aplikovaná statistika, operační výzkum
http://library.utia.cas.cz/separaty/2016/ZS/suzdaleva-0461565.pdf

Classification is one of the frequently demanded tasks in data analysis. There exists a series of approaches in this area. This paper is oriented towards classification using the mixture model estimation, which is based on detection of density clusters in the data space and fitting the component models to them. A chosen function of proximity of the actually measured data to individual mixture components and the component shape play a significant role in solving the mixture-based classification task. This paper considers definitions of the proximity for several types of distributions describing the mixture components and compares their properties with respect to speed and quality of the resulting estimation interpreted as a classification task. Normal, exponential and uniform distributions as the most important models used for describing both Gaussian and non-Gaussian data are considered. Illustrative experiments with results of the comparison are provided.
Trvalý link: http://hdl.handle.net/11104/0261344