Brain computer interface approach using sensor covariance matrix with forced whitening

Hyuksoo Shin, Wonzoo Chung

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    2 Citations (Scopus)

    Abstract

    In this paper, we present a novel motor imagery classification method in electroencephalogmphy (EEG)-based Bmin-Computer lnterfaces (BCIs) using forced whitened sampIe covariance matdces as features. The proposed method performs a constant-forcing to the weaker sources of covadance matrices before a whitening process to prevent amplifications of noise sources which have small power relative to class relevant sources. Expedmental results show the improved accuracy in comparison with a classification without forced whitening process.

    Original languageEnglish
    Title of host publication5th International Winter Conference on Brain-Computer Interface, BCI 2017
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages66-68
    Number of pages3
    ISBN (Electronic)9781509050963
    DOIs
    Publication statusPublished - 2017 Feb 16
    Event5th International Winter Conference on Brain-Computer Interface, BCI 2017 - Gangwon Province, Korea, Republic of
    Duration: 2017 Jan 92017 Jan 11

    Publication series

    Name5th International Winter Conference on Brain-Computer Interface, BCI 2017

    Other

    Other5th International Winter Conference on Brain-Computer Interface, BCI 2017
    Country/TerritoryKorea, Republic of
    CityGangwon Province
    Period17/1/917/1/11

    Keywords

    • Brain-computer interface (BCI)
    • Classification
    • Sensor covariance matrix
    • Supporting vector machine (SVM)
    • Whitening matrix

    ASJC Scopus subject areas

    • Signal Processing
    • Human-Computer Interaction

    Fingerprint

    Dive into the research topics of 'Brain computer interface approach using sensor covariance matrix with forced whitening'. Together they form a unique fingerprint.

    Cite this