1st order class separability using EEG-based features for classification of wrist movements with direction selectivity

M.P. Meckes, F. Sepulveda, B.A. Conway

    Research output: Book/ReportBook

    2 Citations (Scopus)

    Abstract

    28 channel EEG data were recorded while a subject performed wrist movements in four directions. Four feature types were extracted for each channel following optimized filtering of the signals. The potential performance of each feature and channel for use in the classification of the EEG signals was analyzed by estimating the relative class overlap using a first order histogram approach. The best feature/channel configurations contained channels both that were close and far from motor areas. While the scope and depth of the study was very limited, the results do suggest more attention should be paid to non-motor areas when investigating movement related EEG.
    LanguageEnglish
    PublisherIEEE
    ISBN (Print)0-7803-8439-3
    Publication statusPublished - Sep 2004

    Publication series

    NameEngineering in Medicine and Biology Society, 2004. 26th Annual International Conference of the IEEE
    PublisherIEEE

    Fingerprint

    Electroencephalography

    Keywords

    • brain-computer interface
    • movement related potentials
    • pattern recognition
    • EEG
    • biomechanics
    • electroencephalography
    • feature extraction
    • filtering theory
    • medical signal processing
    • signal classification

    Cite this

    Meckes, M. P., Sepulveda, F., & Conway, B. A. (2004). 1st order class separability using EEG-based features for classification of wrist movements with direction selectivity. (Engineering in Medicine and Biology Society, 2004. 26th Annual International Conference of the IEEE). IEEE.
    Meckes, M.P. ; Sepulveda, F. ; Conway, B.A. / 1st order class separability using EEG-based features for classification of wrist movements with direction selectivity. IEEE, 2004. (Engineering in Medicine and Biology Society, 2004. 26th Annual International Conference of the IEEE).
    @book{d3eb5311a44841ffb49181c2233d6916,
    title = "1st order class separability using EEG-based features for classification of wrist movements with direction selectivity",
    abstract = "28 channel EEG data were recorded while a subject performed wrist movements in four directions. Four feature types were extracted for each channel following optimized filtering of the signals. The potential performance of each feature and channel for use in the classification of the EEG signals was analyzed by estimating the relative class overlap using a first order histogram approach. The best feature/channel configurations contained channels both that were close and far from motor areas. While the scope and depth of the study was very limited, the results do suggest more attention should be paid to non-motor areas when investigating movement related EEG.",
    keywords = "brain-computer interface, movement related potentials, pattern recognition, EEG, biomechanics, electroencephalography, feature extraction, filtering theory, medical signal processing, signal classification",
    author = "M.P. Meckes and F. Sepulveda and B.A. Conway",
    year = "2004",
    month = "9",
    language = "English",
    isbn = "0-7803-8439-3",
    series = "Engineering in Medicine and Biology Society, 2004. 26th Annual International Conference of the IEEE",
    publisher = "IEEE",

    }

    Meckes, MP, Sepulveda, F & Conway, BA 2004, 1st order class separability using EEG-based features for classification of wrist movements with direction selectivity. Engineering in Medicine and Biology Society, 2004. 26th Annual International Conference of the IEEE, IEEE.

    1st order class separability using EEG-based features for classification of wrist movements with direction selectivity. / Meckes, M.P.; Sepulveda, F.; Conway, B.A.

    IEEE, 2004. (Engineering in Medicine and Biology Society, 2004. 26th Annual International Conference of the IEEE).

    Research output: Book/ReportBook

    TY - BOOK

    T1 - 1st order class separability using EEG-based features for classification of wrist movements with direction selectivity

    AU - Meckes, M.P.

    AU - Sepulveda, F.

    AU - Conway, B.A.

    PY - 2004/9

    Y1 - 2004/9

    N2 - 28 channel EEG data were recorded while a subject performed wrist movements in four directions. Four feature types were extracted for each channel following optimized filtering of the signals. The potential performance of each feature and channel for use in the classification of the EEG signals was analyzed by estimating the relative class overlap using a first order histogram approach. The best feature/channel configurations contained channels both that were close and far from motor areas. While the scope and depth of the study was very limited, the results do suggest more attention should be paid to non-motor areas when investigating movement related EEG.

    AB - 28 channel EEG data were recorded while a subject performed wrist movements in four directions. Four feature types were extracted for each channel following optimized filtering of the signals. The potential performance of each feature and channel for use in the classification of the EEG signals was analyzed by estimating the relative class overlap using a first order histogram approach. The best feature/channel configurations contained channels both that were close and far from motor areas. While the scope and depth of the study was very limited, the results do suggest more attention should be paid to non-motor areas when investigating movement related EEG.

    KW - brain-computer interface

    KW - movement related potentials

    KW - pattern recognition

    KW - EEG

    KW - biomechanics

    KW - electroencephalography

    KW - feature extraction

    KW - filtering theory

    KW - medical signal processing

    KW - signal classification

    UR - http://dx.doi.org/10.1109/IEMBS.2004.1404218

    M3 - Book

    SN - 0-7803-8439-3

    T3 - Engineering in Medicine and Biology Society, 2004. 26th Annual International Conference of the IEEE

    BT - 1st order class separability using EEG-based features for classification of wrist movements with direction selectivity

    PB - IEEE

    ER -

    Meckes MP, Sepulveda F, Conway BA. 1st order class separability using EEG-based features for classification of wrist movements with direction selectivity. IEEE, 2004. (Engineering in Medicine and Biology Society, 2004. 26th Annual International Conference of the IEEE).