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

An expectation-maximization method for spatio-temporal blind source separation using an AR-MOG source model.

Kenneth E Hild1, Hagai T Attias, Srikantan S Nagarajan

  • 1Department of Radiology, The University of California at San Francisco, San Francisco, CA 94143, USA. k.hild@ieee.org

IEEE Transactions on Neural Networks
|March 13, 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

Global Signal Removal (GSR) as graph spatial filtering.

bioRxiv : the preprint server for biology·2026
Same author

Thalamic connectivity mirrors spatial maps of network dysfunction in nonlesional focal epilepsy.

Epilepsia·2026
Same author

Enhanced pitch centering in individuals with laryngeal dystonia.

Frontiers in human neuroscience·2026
Same author

Abnormal hippocampo-cortical theta-gamma phase-amplitude coupling in Alzheimer's disease.

medRxiv : the preprint server for health sciences·2026
Same author

Reduced cortical excitability is associated with head impact severity and cognitive symptoms in adolescent football players.

iScience·2026
Same author

Adaptation response to pitch shift during speech is attenuated upon relearning.

Frontiers in human neuroscience·2026
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

A new maximum-likelihood (ML) algorithm, autoregressive mixture of Gaussians (AR-MOG), separates mixed signals using spatial and temporal data. This blind source separation (BSS) method excels in audio and fetal magnetocardiography (MCG) signal extraction.

Area of Science:

  • Signal Processing
  • Machine Learning
  • Biomedical Engineering

Background:

  • Blind Source Separation (BSS) is crucial for isolating signals from mixed recordings.
  • Existing methods often neglect temporal dependencies or complex source distributions.
  • Maximum Likelihood (ML) approaches offer a principled framework for BSS.

Purpose of the Study:

  • To develop a novel ML-based spatio-temporal BSS algorithm.
  • To incorporate autoregressive (AR) temporal models and Gaussian mixture distributions for source signals.
  • To improve BSS performance by leveraging both spatial and temporal information.

Main Methods:

  • Developed a maximum-likelihood (ML) algorithm named Autoregressive Mixture of Gaussians (AR-MOG).
  • Modeled temporal dependencies using autoregressive (AR) processes.

Related Experiment Videos

  • Utilized a mixture of Gaussians to describe the innovations process.
  • Employed the expectation-maximization (EM) algorithm for optimization.

    • Main Results:

    • The AR-MOG algorithm demonstrated superior performance compared to nine other methods on artificial audio mixtures.
    • The method effectively extracted the fetal cardiac signal from real magnetocardiographic (MCG) data.
    • The algorithm's update equations were derived in a simple, analytical form.

    Conclusions:

    • The proposed AR-MOG algorithm offers an effective approach for spatio-temporal blind source separation.
    • Integrating AR models and Gaussian mixtures enhances BSS performance.
    • AR-MOG shows promise for applications in audio processing and biomedical signal analysis, such as MCG.