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

Directed EEG neural network analysis by LAPPS (p≤1) Penalized sparse Granger approach.

Joyce Chelangat Bore1, Peiyang Li2, Dennis Joe Harmah1

  • 1The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu 611731, People's Republic of China.

Neural Networks : the Official Journal of the International Neural Network Society
|February 5, 2020
PubMed
Summary

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

Neurostructural subgroup in 4291 individuals with schizophrenia identified using the subtype and stage inference algorithm.

Nature communications·2024
Same author

Reliable object tracking by multimodal hybrid feature extraction and transformer-based fusion.

Neural networks : the official journal of the International Neural Network Society·2024
Same author

Temporal Dynamic Synchronous Functional Brain Network for Schizophrenia Classification and Lateralization Analysis.

IEEE transactions on medical imaging·2024
Same author

Neuroimaging epicenters as potential sites of onset of the neuroanatomical pathology in schizophrenia.

Science advances·2024
Same author

An Efficient Graph Learning System for Emotion Recognition Inspired by the Cognitive Prior Graph of EEG Brain Network.

IEEE transactions on neural networks and learning systems·2024
Same author

Large-Scale Cortical Network Analysis and Classification of MI-BCI Tasks Based on Bayesian Nonnegative Matrix Factorization.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2024

This study introduces LAPPS, a novel Granger Analysis method robust to noise in brain network construction. LAPPS effectively identifies sparse brain networks from EEG data, even with significant interference.

Area of Science:

  • Neuroscience
  • Signal Processing
  • Network Science

Background:

  • Conventional Granger Analysis (GA) for brain network construction using EEG/fMRI is susceptible to noise, leading to distortions.
  • The L2-norm in standard GAs struggles with noisy EEG data, impacting directed network recovery.
  • Lp-norm (p ≤ 1) methods offer improved robustness to outliers compared to L2-GAs and LASSO.

Purpose of the Study:

  • To develop a robust Granger Analysis method for constructing sparse brain networks from noisy EEG data.
  • Introduce LAPPS (Least Absolute Lp Penalized Solution) to overcome limitations of existing GA methods under high noise conditions.

Main Methods:

  • Developed LAPPS, utilizing an L1-loss function for residual errors to mitigate outlier effects.
  • Employed an Lp-penalty term (p=0.5) within LAPPS for sparse connection identification and suppression of spurious linkages.
Keywords:
Motor ImageryMultivariate Granger AnalysisOutliersSparse network

Related Experiment Videos

  • Validated LAPPS using simulations across various noise levels and real EEG data from Motor Imagery (MI) tasks.

    • Main Results:

    • LAPPS demonstrated superior performance in simulation studies under diverse noise conditions.
    • Analysis of real EEG data during Motor Imagery tasks revealed LAPPS successfully generated sparse brain networks.
    • Identified contralateral primary motor areas as network hubs, consistent with the neurophysiological basis of MI.

    Conclusions:

    • LAPPS provides a robust and effective approach for brain network analysis using noisy EEG data.
    • The method successfully constructs sparse networks, accurately reflecting brain activity during tasks like Motor Imagery.
    • LAPPS offers a significant advancement for brain connectivity research, particularly with challenging EEG datasets.