Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Implementing EM and Viterbi algorithms for Hidden Markov Model in linear memory.

Alexander Churbanov1, Stephen Winters-Hilt

  • 1The Research Institute for Children, 200 Henry Clay Ave, New Orleans, LA 70118, USA. achurbanov@yahoo.com

BMC Bioinformatics
|May 2, 2008
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Nanopore Event-Transduction Signal Stabilization for Wide pH Range under Extreme Chaotrope Conditions.

Molecules (Basel, Switzerland)·2016
Same author

Virus-host mucosal interactions during early SIV rectal transmission.

Virology·2014
Same author

A novel splice-site mutation in angiotensin I-converting enzyme (ACE) gene, c.3691+1G>A (IVS25+1G>A), causes a dramatic increase in circulating ACE through deletion of the transmembrane anchor.

PloS one·2013
Same author

Accurate diagnostics for Bovine tuberculosis based on high-throughput sequencing.

PloS one·2012
Same author

HighSSR: high-throughput SSR characterization and locus development from next-gen sequencing data.

Bioinformatics (Oxford, England)·2012
Same author

The NTD Nanoscope: potential applications and implementations.

BMC bioinformatics·2011
Same journal

OpenIMC: an open-source platform for analyzing single-cell and spatial proteomics by imaging mass cytometry.

BMC bioinformatics·2026
Same journal

NAP: an open source pipeline for cross-domain microbiome profiling using Nanopore sequencing-derived amplicon data.

BMC bioinformatics·2026
Same journal

SurvGME: an R package for survival analysis with graphical and measurement error models.

BMC bioinformatics·2026
Same journal

SimMapNet: a Bayesian framework for gene regulatory network inference using gene ontology similarities as external hint.

BMC bioinformatics·2026
Same journal

Dual channel drug-drug interactions extraction based on cross attention.

BMC bioinformatics·2026
Same journal

FeSseqdb: a curated sequence-level database and interpretable machine learning framework for identifying iron-sulfur proteins.

BMC bioinformatics·2026
See all related articles

We corrected and improved the linear memory Baum-Welch algorithm for Hidden Markov Models (HMMs), enhancing its efficiency for large datasets. Our optimized implementations offer practical solutions for various sequence analysis tasks.

Area of Science:

  • Computational biology
  • Machine learning
  • Bioinformatics

Background:

  • The Baum-Welch algorithm is crucial for Hidden Markov Models (HMMs) in knowledge discovery and clustering.
  • A linear memory version exists but contains errors.
  • This study corrects and refines the linear memory Baum-Welch algorithm.

Purpose of the Study:

  • To amend errors in the linear memory Baum-Welch algorithm.
  • To compare corrected implementations with conventional and checkpointing methods.
  • To develop efficient linear memory Viterbi decoding.

Main Methods:

  • Corrected recurrence relation for emission parameter estimation.
  • Extended to Normal distribution parameter estimates.
  • Reversed forward sweep for accelerated prior state probability estimation.

Related Experiment Videos

  • Implemented scaling strategies to prevent underflow.
  • Developed linear memory Viterbi decoding algorithm.

    • Main Results:

    • The checkpointing algorithm offers the best balance of memory and speed.
    • Linear memory methods are useful for very large sequence lengths (Baum-Welch) or state numbers (Viterbi).
    • Demonstrated utility on extended Duration Hidden Markov Models and spike detection topologies.

    Conclusions:

    • Performance-optimized Java implementations of the Baum-Welch algorithm are available.
    • The methods aid sequence alignment, gene structure prediction, and HMM profile training.
    • Applicable to nanopore ionic flow blockades analysis and other EM-based HMM training domains.