Identifying complex brain networks using penalized regression methods

Eduardo Martínez-Montes, Mayrim Vega-Hernández, José M. Sánchez-Bornot, Pedro A. Valdés-Sosa

    Research output: Contribution to journalArticle

    10 Citations (Scopus)

    Abstract

    The recorded electrical activity of complex brain networks through the EEG reflects their intrinsic spatial, temporal and spectral properties. In this work we study the application of new penalized regression methods to i) the spatial characterization of the brain networks associated with the identification of faces and ii) the PARAFAC analysis of resting-state EEG. The use of appropriate constraints through non-convex penalties allowed three types of inverse solutions (Loreta, Lasso Fusion and ENet L) to spatially localize networks in agreement with previous studies with fMRI. Furthermore, we propose a new penalty based in the Information Entropy for the constrained PARAFAC analysis of resting EEG that allowed the identification in time, frequency and space of those brain networks with minimum spectral entropy. This study is an initial attempt to explicitly include complexity descriptors as a constraint in multilinear EEG analysis.

    LanguageEnglish
    Pages315-323
    Number of pages9
    JournalJournal of Biological Physics
    Volume34
    Issue number3-4 SPEC. ISS.
    DOIs
    Publication statusPublished - 1 Aug 2008

    Fingerprint

    electroencephalography
    brain
    regression analysis
    Electroencephalography
    Brain
    Entropy
    penalties
    entropy
    fusion
    Magnetic Resonance Imaging

    Keywords

    • Complex brain networks
    • EEG inverse problem
    • Information Entropy
    • Multiple penalized least squares model
    • PARAFAC

    Cite this

    Martínez-Montes, Eduardo ; Vega-Hernández, Mayrim ; Sánchez-Bornot, José M. ; Valdés-Sosa, Pedro A. / Identifying complex brain networks using penalized regression methods. In: Journal of Biological Physics. 2008 ; Vol. 34, No. 3-4 SPEC. ISS. pp. 315-323.
    @article{1da7e0c444924d6893b4f7dd2295e0eb,
    title = "Identifying complex brain networks using penalized regression methods",
    abstract = "The recorded electrical activity of complex brain networks through the EEG reflects their intrinsic spatial, temporal and spectral properties. In this work we study the application of new penalized regression methods to i) the spatial characterization of the brain networks associated with the identification of faces and ii) the PARAFAC analysis of resting-state EEG. The use of appropriate constraints through non-convex penalties allowed three types of inverse solutions (Loreta, Lasso Fusion and ENet L) to spatially localize networks in agreement with previous studies with fMRI. Furthermore, we propose a new penalty based in the Information Entropy for the constrained PARAFAC analysis of resting EEG that allowed the identification in time, frequency and space of those brain networks with minimum spectral entropy. This study is an initial attempt to explicitly include complexity descriptors as a constraint in multilinear EEG analysis.",
    keywords = "Complex brain networks, EEG inverse problem, Information Entropy, Multiple penalized least squares model, PARAFAC",
    author = "Eduardo Mart{\'i}nez-Montes and Mayrim Vega-Hern{\'a}ndez and S{\'a}nchez-Bornot, {Jos{\'e} M.} and Vald{\'e}s-Sosa, {Pedro A.}",
    year = "2008",
    month = "8",
    day = "1",
    doi = "10.1007/s10867-008-9077-0",
    language = "English",
    volume = "34",
    pages = "315--323",
    journal = "Journal of Biological Physics",
    issn = "0092-0606",
    number = "3-4 SPEC. ISS.",

    }

    Martínez-Montes, E, Vega-Hernández, M, Sánchez-Bornot, JM & Valdés-Sosa, PA 2008, 'Identifying complex brain networks using penalized regression methods', Journal of Biological Physics, vol. 34, no. 3-4 SPEC. ISS., pp. 315-323. https://doi.org/10.1007/s10867-008-9077-0

    Identifying complex brain networks using penalized regression methods. / Martínez-Montes, Eduardo; Vega-Hernández, Mayrim; Sánchez-Bornot, José M.; Valdés-Sosa, Pedro A.

    In: Journal of Biological Physics, Vol. 34, No. 3-4 SPEC. ISS., 01.08.2008, p. 315-323.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Identifying complex brain networks using penalized regression methods

    AU - Martínez-Montes, Eduardo

    AU - Vega-Hernández, Mayrim

    AU - Sánchez-Bornot, José M.

    AU - Valdés-Sosa, Pedro A.

    PY - 2008/8/1

    Y1 - 2008/8/1

    N2 - The recorded electrical activity of complex brain networks through the EEG reflects their intrinsic spatial, temporal and spectral properties. In this work we study the application of new penalized regression methods to i) the spatial characterization of the brain networks associated with the identification of faces and ii) the PARAFAC analysis of resting-state EEG. The use of appropriate constraints through non-convex penalties allowed three types of inverse solutions (Loreta, Lasso Fusion and ENet L) to spatially localize networks in agreement with previous studies with fMRI. Furthermore, we propose a new penalty based in the Information Entropy for the constrained PARAFAC analysis of resting EEG that allowed the identification in time, frequency and space of those brain networks with minimum spectral entropy. This study is an initial attempt to explicitly include complexity descriptors as a constraint in multilinear EEG analysis.

    AB - The recorded electrical activity of complex brain networks through the EEG reflects their intrinsic spatial, temporal and spectral properties. In this work we study the application of new penalized regression methods to i) the spatial characterization of the brain networks associated with the identification of faces and ii) the PARAFAC analysis of resting-state EEG. The use of appropriate constraints through non-convex penalties allowed three types of inverse solutions (Loreta, Lasso Fusion and ENet L) to spatially localize networks in agreement with previous studies with fMRI. Furthermore, we propose a new penalty based in the Information Entropy for the constrained PARAFAC analysis of resting EEG that allowed the identification in time, frequency and space of those brain networks with minimum spectral entropy. This study is an initial attempt to explicitly include complexity descriptors as a constraint in multilinear EEG analysis.

    KW - Complex brain networks

    KW - EEG inverse problem

    KW - Information Entropy

    KW - Multiple penalized least squares model

    KW - PARAFAC

    UR - http://www.scopus.com/inward/record.url?scp=56749140717&partnerID=8YFLogxK

    U2 - 10.1007/s10867-008-9077-0

    DO - 10.1007/s10867-008-9077-0

    M3 - Article

    VL - 34

    SP - 315

    EP - 323

    JO - Journal of Biological Physics

    T2 - Journal of Biological Physics

    JF - Journal of Biological Physics

    SN - 0092-0606

    IS - 3-4 SPEC. ISS.

    ER -