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

MEG source localization using an MLP with a distributed output representation.

Sung Chan Jun1, Barak A Pearlmutter, Guido Nolte

  • 1Biological & Quantum Physics Group, MS-D454, Los Alamos National Laboratory, Los Alamos, NM 87545, USA. jschan@lanl.gov

IEEE Transactions on Bio-Medical Engineering
|June 20, 2003
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

EEG-Based Pain Classification via Sample Selection to Mitigate Subjective Label Bias.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026
Same author

Low-rank tensor decomposition for cross-bispectral analysis of EEG data.

Journal of neuroscience methods·2026
Same author

Intensity-dependent tACS entrainment effects in a cortical microcircuit: a computational study.

Scientific reports·2026
Same author

A 40-Class SSVEP Speller Dataset: Beta Range Stimulation for Low-Fatigue BCI Applications.

Scientific data·2025
Same author

Source to sensor coupling (SoSeC) as an effective tool to localize interacting sources from EEG and MEG data.

Journal of neuroscience methods·2025
Same author

Predictive role of endogenous phase lags between target brain regions in dual-site transcranial alternating current stimulation.

Brain stimulation·2025
Same journal

Enhancing Volumetric Imaging in Linear-Array Photoacoustic Tomography: multiview fusion with deep learning.

IEEE transactions on bio-medical engineering·2026
Same journal

Robust Rule-based Heuristic Assistance Strategy for a Semi-Active Shoulder Exoskeleton Used in Overhead Work.

IEEE transactions on bio-medical engineering·2026
Same journal

Highly Accelerated 1-mm Isotropic 3D Chemical Exchange Saturation Transfer MRI Using Wave-Co-CAIPI at 5 Tesla.

IEEE transactions on bio-medical engineering·2026
Same journal

Systematic Evaluation of Hip Exoskeleton Assistance Parameters for Enhancing Gait Stability During Ground Slip Perturbations.

IEEE transactions on bio-medical engineering·2026
Same journal

SleepConFormer: A Single-Channel EEG Framework for Sleep Staging and Consciousness Assessment in Patients with Disorders of Consciousness.

IEEE transactions on bio-medical engineering·2026
Same journal

Modeling Partial and Total Support of Left Ventricular Assist Device for Discrete Hemodynamic Control Framework.

IEEE transactions on bio-medical engineering·2026
See all related articles

This study introduces a novel system using a Soft-Multilayer Perceptron (MLP) for real-time magnetoencephalographic (MEG) signal analysis. The system accurately localizes brain activity sources with improved efficiency over existing methods.

Area of Science:

  • Neuroscience
  • Biophysics
  • Machine Learning

Background:

  • Magnetoencephalography (MEG) is crucial for non-invasive brain activity measurement.
  • Accurate real-time source localization remains a challenge in MEG data analysis.
  • Current methods often lack the precision required for detailed neural activity mapping.

Purpose of the Study:

  • To develop and validate a novel system for accurate, real-time single dipole localization using MEG signals.
  • To enhance the accuracy and computational efficiency of neural source localization techniques.
  • To compare the performance of the proposed system against conventional methods.

Main Methods:

  • Utilized a Soft-Multilayer Perceptron (MLP) with sensor measurements as input and receptive field amplitudes as output.

Related Experiment Videos

  • Trained the MLP on simulated dipolar sources with realistic brain noise.
  • Employed two decoding strategies to convert network output into Cartesian dipole coordinates.
  • Investigated hybrid systems combining Soft-MLP with Levenberg-Marquardt (LM) optimization.

    • Main Results:

    • The Soft-MLP system achieved reasonable accuracy in real-time dipole localization.
    • Proposed Soft-MLPs demonstrated superior accuracy compared to prior Cartesian coordinate output networks.
    • Hybrid Soft-MLP-LM systems maintained high accuracy (0.28 cm) while reducing computation time from 36 ms to 30 ms.
    • Applied the system to real MEG data, showing comparable performance to conventional methods.

    Conclusions:

    • The Soft-MLP system offers a significant advancement in real-time MEG source localization.
    • Hybrid Soft-MLP-LM approaches provide an efficient and accurate solution for neural source identification.
    • This technology holds promise for improving the analysis of complex brain activity.