A Bidirectional Hidden Markov Model in Linear Memory
|
Nasim Ejlali, Hamid Pezeshk |
|
|
Abstract: (18127 Views) |
Hidden Markov models are widely used in Bioinformatics. They are applied to protein sequence alignment,
protein family annotation and gene-finding.The Baum-Welch training is an expectation-maximization algorithm for training
the emission and transition probabilities of hidden Markov models. For very long training sequence, even the most
efficient algorithms are memory-consuming. In this paper we discuss different approaches to decrease the memory use
and compare the performance of different algorithms.
In addition, we propose a bidirection algorithm with linear memory. We apply this algorithm to simulated
data of protein profile to analyze the strength and weakness of the algorithm. |
|
Keywords: Hidden Markov Models, Baum-Welch Algorithm, Bidirectional Model, Profile Hidden Markov Model, Linear Memory. |
|
Full-Text [PDF 611 kb]
(3507 Downloads)
|
Type of Study: Research |
Subject:
Probability & Stochastic Processes Received: 2011/07/4 | Accepted: 2013/08/13 | Published: 2020/02/18
|
|
|
|
|
Add your comments about this article |
|
|