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

Graphical representation of multidimensional EEG data and classificatory aspects.

T Gasser, J Möcks

    Electroencephalography and Clinical Neurophysiology
    |May 1, 1983
    PubMed
    Summary

    Non-metric multidimensional scaling (MDS) and principal component analysis (PCA) reduce complex EEG data. MDS showed superiority for analyzing neurophysiological data in learning disabilities.

    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

    Reduced Complexity Model Intercomparison Project Phase 2: Synthesizing Earth System Knowledge for Probabilistic Climate Projections.

    Earth's future·2021
    Same author

    Integrated molecular landscape of Parkinson's disease.

    NPJ Parkinson's disease·2017
    Same author

    [Genetic risk factors for neuropsychiatric disorders].

    Der Nervenarzt·2017
    Same author

    [Stereotactic laser thermocoagulation in epilepsy surgery].

    Der Nervenarzt·2017
    Same author

    Inflammatory profile discriminates clinical subtypes in LRRK2-associated Parkinson's disease.

    European journal of neurology·2017
    Same author

    Rare variants analysis of cutaneous malignant melanoma genes in Parkinson's disease.

    Neurobiology of aging·2016

    Area of Science:

    • Neuroscience
    • Data Analysis
    • Biostatistics

    Background:

    • Electroencephalography (EEG) data possess inherent multidimensional characteristics.
    • Spectral parameters derived from EEG present a complex, high-dimensional dataset.
    • Effective dimensionality reduction is crucial for group comparison and subgroup identification in EEG studies.

    Purpose of the Study:

    • To compare Non-metric Multidimensional Scaling (MDS) and Principal Component Analysis (PCA) for EEG data dimensionality reduction.
    • To evaluate the efficacy of these methods in graphical comparison and subgroup identification.
    • To assess the utility of (1-p)-convex hulls in defining normative regions within reduced dimensional spaces.

    Main Methods:

    • Application of Non-metric Multidimensional Scaling (MDS) to broad band spectral EEG parameters.

    Related Experiment Videos

  • Application of Principal Component Analysis (PCA) to the same EEG parameters.
  • Utilizing (1-p)-convex hulls to delineate normative regions for data visualization.

    • Main Results:

    • MDS demonstrated slightly superior performance compared to PCA in representing EEG data structure.
    • Both MDS and PCA benefited from the incorporation of (1-p)-convex hulls for defining normative boundaries.
    • The study successfully applied these dimensionality reduction techniques to neurophysiological data related to mental retardation and learning disability.

    Conclusions:

    • Non-metric Multidimensional Scaling (MDS) offers advantages over PCA for analyzing complex, multidimensional EEG spectral data.
    • The integration of (1-p)-convex hulls enhances the interpretability and utility of dimensionality reduction techniques in EEG research.
    • These findings have implications for the neurophysiological analysis of learning disabilities and related conditions.