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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Ancestry informative genetic variants associated with tobacco metabolic and detoxification capacity measured by 4-(methylnitrosamino)-1-(3-pyridyl)-1-butanol (NNAL) among smokers.

Archives of toxicology·2026
Same author

Influence of surgical intervention on pre- and post-surgery patient specific muscle synergies in children with cerebral palsy.

Experimental brain research·2026
Same author

Functional symmetrization of neuromotor modules during locomotor development in human infants.

Communications biology·2025
Same author

State-dependent neural representations of muscle synergies in the spinal cord revealed by optogenetic stimulation.

The Journal of physiology·2025
Same author

Muscle Synergy Analysis for Clinical Characterization of Upper Limb Motor Recovery After Stroke.

Archives of physical medicine and rehabilitation·2025
Same author

Frequency-Aware Spatial-Temporal Attention Explainable Network for EEG Decoding.

IEEE journal of biomedical and health informatics·2025

Related Experiment Video

Updated: May 1, 2026

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

44.0K

On nonnegative matrix factorization algorithms for signal-dependent noise with application to electromyography data.

Karthik Devarajan1, Vincent C K Cheung

  • 1Department of Biostatistics and Bioinformatics, Fox Chase Cancer Center, Philadelphia, PA 19111, U.S.A. karthik.devarajan@fccc.edu.

Neural Computation
|April 2, 2014
PubMed
Summary

This study introduces novel nonnegative matrix factorization (NMF) algorithms using an information-theoretic approach for signal-dependent noise. These methods enhance data analysis in fields like neuroscience and biology.

More Related Videos

Repeated Measurement of Respiratory Muscle Activity and Ventilation in Mouse Models of Neuromuscular Disease
09:24

Repeated Measurement of Respiratory Muscle Activity and Ventilation in Mouse Models of Neuromuscular Disease

Published on: April 17, 2017

12.9K
Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research
08:33

Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research

Published on: January 5, 2024

2.0K

Related Experiment Videos

Last Updated: May 1, 2026

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

44.0K
Repeated Measurement of Respiratory Muscle Activity and Ventilation in Mouse Models of Neuromuscular Disease
09:24

Repeated Measurement of Respiratory Muscle Activity and Ventilation in Mouse Models of Neuromuscular Disease

Published on: April 17, 2017

12.9K
Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research
08:33

Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research

Published on: January 5, 2024

2.0K

Area of Science:

  • Machine Learning
  • Signal Processing
  • Computational Biology

Background:

  • Nonnegative matrix factorization (NMF) is a machine learning technique for matrix decomposition (V ≈ WH).
  • NMF's nonnegativity constraints enable learning additive, physically interpretable components from data.
  • Existing NMF methods face challenges with signal-dependent noise.

Discussion:

  • This work proposes an information-theoretic NMF approach using the generalized inverse Gaussian model for signal-dependent noise.
  • Three novel multiplicative update algorithms are presented, with proven monotonicity via the Expectation-Maximization (EM) algorithm.
  • Algorithm-specific goodness-of-fit measures are developed for performance evaluation.

Key Insights:

  • The novel NMF algorithms effectively handle signal-dependent noise.
  • Demonstrated success in analyzing electromyography (EMG) data and extracting muscle synergies from simulated data.
  • The proposed methods show competitive performance compared to existing algorithms for signal-dependent noise.

Outlook:

  • Potential for broader applications in signal processing and large-scale data analysis.
  • Further research could explore extensions to different noise models and NMF variants.
  • Integration into advanced computational biology and neuroscience research pipelines.