The Training Algorithm of Fuzzy Coupled Hidden Markov Models

2014 ◽  
Vol 568-570 ◽  
pp. 254-259
Author(s):  
Shi Ping Du ◽  
Jian Wang ◽  
Yu Ming Wei
Keyword(s):  
Hidden Markov Models ◽  
Markov Models ◽  
Hidden Markov ◽  
Statistical Modelling ◽  
Fuzzy Entropy ◽  
Training Algorithms ◽  
State Variables ◽  
Fuzzy C Means ◽  
Coupled Hidden Markov Models ◽  
Modelling Techniques

A variety of coupled hidden Markov models (CHMMs) have recently been proposed as extensions of HMM to better characterize multiple interdependent sequences. The resulting models have multiple state variables that are temporally coupled via matrices of conditional probabilities. A generalised fuzzy approach to statistical modelling techniques is proposed in this paper. Fuzzy C-means (FCM) and fuzzy entropy (FE) techniques are combined into a generalised fuzzy technique and applied to coupled hidden Markov models. The CHMM based on the fuzzy c-means (FCM) and fuzzy entropy (FE) is referred to as FCM-FE-CHMM in this paper. By building up a generalised fuzzy objective function, several new formulae solving Training algorithms are theoretically derived for FCM-FE-CHMM. The fuzzy modelling techniques are very flexible since the degree of fuzziness, the degree of fuzzy entropy.

The Learning Algorithms of Coupled Discrete Hidden Markov Models

2013 ◽  
Vol 411-414 ◽  
pp. 2106-2110
Author(s):  
Shi Ping Du ◽  
Jian Wang ◽  
Yu Ming Wei
Keyword(s):  
Hidden Markov Models ◽  
Viterbi Algorithm ◽  
Markov Models ◽  
Hidden Markov ◽  
Process Models ◽  
State Variables ◽  
Biological Sequence ◽  
Training Problem ◽  
Biological Sequence Analysis ◽  
Coupled Hidden Markov Models

A hidden Markov model (HMM) encompasses a large class of stochastic process models and has been successfully applied to a number of scientific and engineering problems, including speech and other pattern recognition problems, and biological sequence analysis. A major restriction is found, however, in conventional HMM, i.e., it is ill-suited to capture the interactions among different models. A variety of coupled hidden Markov models (CHMMs) have recently been proposed as extensions of HMM to better characterize multiple interdependent sequences. The resulting models have multiple state variables that are temporally coupled via matrices of conditional probabilities. This paper study is focused on the coupled discrete HMM, there are two state variables in the network. By generalizing forward-backward algorithm, Viterbi algorithm and Baum-Welch algorithm commonly used in conventional HMM to accommodate two state variables, several new formulae solving the 2-chain coupled discrete HMM probability evaluation, decoding and training problem are theoretically derived.

Audio-visual speech asynchrony detection using co-inertia analysis and coupled hidden markov models

2008 ◽  
Vol 12 (3) ◽  
pp. 271-284 ◽  
Author(s):  
Enrique Argones Rúa ◽  
Hervé Bredin ◽  
Carmen García Mateo ◽  
Gérard Chollet ◽  
Daniel González Jiménez
Keyword(s):  
Hidden Markov Models ◽  
Markov Models ◽  
Hidden Markov ◽  
Visual Speech ◽  
Coupled Hidden Markov Models ◽  
Asynchrony Detection

scholarly journals Variational Inference for Coupled Hidden Markov Models Applied to the Joint Detection of Copy Number Variations

2019 ◽  
Vol 15 (1) ◽  
Author(s):  
Xiaoqiang Wang ◽  
Emilie Lebarbier ◽  
Julie Aubert ◽  
Stéphane Robin
Keyword(s):  
Hidden Markov Models ◽  
Copy Number ◽  
Markov Models ◽  
Hidden Markov ◽  
R Package ◽  
Copy Number Variations ◽  
Structural Variations ◽  
Statistical Framework ◽  
Coupled Hidden Markov Models ◽  
Hidden Markov Process

Abstract Hidden Markov models provide a natural statistical framework for the detection of the copy number variations (CNV) in genomics. In this context, we define a hidden Markov process that underlies all individuals jointly in order to detect and to classify genomics regions in different states (typically, deletion, normal or amplification). Structural variations from different individuals may be dependent. It is the case in agronomy where varietal selection program exists and species share a common phylogenetic past. We propose to take into account these dependencies inthe HMM model. When dealing with a large number of series, maximum likelihood inference (performed classically using the EM algorithm) becomes intractable. We thus propose an approximate inference algorithm based on a variational approach (VEM), implemented in the CHMM R package. A simulation study is performed to assess the performance of the proposed method and an application to the detection of structural variations in plant genomes is presented.

Sign in / Sign up

Export Citation Format

Share Document