Please use this identifier to cite or link to this item: http://ktisis.cut.ac.cy/handle/10488/7261
Title: Hidden Markov models with nonelliptically contoured state densities
Authors: Chatzis, Sotirios P. 
Chatzis, Sotirios P. 
Keywords: Markov processes
Artificial intelligence
Gaussian distribution
Issue Date: 2010
Publisher: IEEE Xplore
Source: IEEE transactions on pattern analysis and machine intelligence, 2010, Volume 32, Issue 12, 2010, Pages 2297-2304
Abstract: Hidden Markov models (HMMs) are a popular approach for modeling sequential data comprising continuous attributes. In such applications, the observation emission densities of the HMM hidden states are typically modeled by means of elliptically contoured distributions, usually multivariate Gaussian or Student's-t densities. However, elliptically contoured distributions cannot sufficiently model heavy-tailed or skewed populations which are typical in many fields, such as the financial and the communication signal processing domain. Employing finite mixtures of such elliptically contoured distributions to model the HMM state densities is a common approach for the amelioration of these issues. Nevertheless, the nature of the modeled data often requires postulation of a large number of mixture components for each HMM state, which might have a negative effect on both model efficiency and the training data set's size required to avoid overfitting. To resolve these issues, in this paper, we advocate for the utilization of a nonelliptically contoured distribution, the multivariate normal inverse Gaussian (MNIG) distribution, for modeling the observation densities of HMMs. As we experimentally demonstrate, our selection allows for more effective modeling of skewed and heavy-tailed populations in a simple and computationally efficient manner
URI: http://ktisis.cut.ac.cy/handle/10488/7261
ISSN: 01628828
DOI: 10.1109/TPAMI.2010.153
Rights: © 2010 IEEE
Appears in Collections:Άρθρα/Articles

Show full item record

SCOPUSTM   
Citations 20

8
checked on Dec 29, 2016

WEB OF SCIENCETM
Citations 50

3
checked on Dec 27, 2016

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.