Article citationsMore >>

Khreich W., Granger E, Miri A., Sabourin R., "On the memory complexity of the forward–backward algorithm," Pattern Recognition Letters 31. 2010.

has been cited by the following article:

Article

Some Algorithms for Large Hidden Markov Models

1University Sultan Moulay Slimane, Laboratory of modelisation and calcul, Béni Mellal


World Journal Control Science and Engineering. 2013, Vol. 1 No. 1, 9-14
DOI: 10.12691/wjcse-1-1-2
Copyright © 2013 Science and Education Publishing

Cite this paper:
Sanaa Chafik, Daoui Cherki. Some Algorithms for Large Hidden Markov Models. World Journal Control Science and Engineering. 2013; 1(1):9-14. doi: 10.12691/wjcse-1-1-2.

Correspondence to: Sanaa Chafik, University Sultan Moulay Slimane, Laboratory of modelisation and calcul, Béni Mellal. Email: san.chafik@gmail.com

Abstract

The Hidden Markov Model (HMM) has become increasingly popular in the last several years because it is used in a wide range of applications. There are some inherent limitations of this type of statistical model. The major limitation of HMM is large hidden state space, which limits their practical purview. The objective of this work is to reduce the task of solving some classical algorithms (Forward, Backward, Baum-Welch) by review of their theoretical aspects, offering faster improved algorithms based on the decomposition technique which represent a general approach to solving a problem by breaking it up into smaller ones and solving each of the smaller ones separately.

Keywords