MURAL - Maynooth University Research Archive Library



    A novel co-locational and concurrent fNIRS/EEG measurement system: design and initial results.


    Leamy, Darren J. and Ward, Tomas E. (2010) A novel co-locational and concurrent fNIRS/EEG measurement system: design and initial results. In: 32nd Annual International Conference of the IEEE EMBS, August 31 - September 4, 2010, Buenos Aires, Argentina..

    [img] Download (539kB)


    Share your research

    Twitter Facebook LinkedIn GooglePlus Email more...



    Add this article to your Mendeley library


    Abstract

    We describe here the design, set-up and first time classification results of a novel co-locational functional Near- Infrared Spectroscopy/Electroencephalography (fNIRS/EEG) recording device suitable for brain computer interfacing applications using neural-hemodynamic signals. Our dual-modality system recorded both hemodynamic and electrical activity at seven sites over the motor cortex during an overt finger-tapping task. Data was collected from two subjects and classified offline using Linear Discriminant Analysis (LDA) and Leave-One-Out Cross-Validation (LOOCV). Classification of fNIRS features, EEG features and a combination of fNIRS/EEG features were performed separately. Results illustrate that classification of the combined fNIRS/EEG feature space offered average improved performance over classification of either feature space alone. The complementary nature of the physiological origin of the dual measurements offer a unique and information rich signal for a small measurement area of cortex. We feel this technology may be particularly useful in the design of BCI devices for the augmentation of neurorehabilitation therapy.

    Item Type: Conference or Workshop Item (Paper)
    Keywords: fNIRS/EEG measurement system; design and initial results;
    Academic Unit: Faculty of Science and Engineering > Electronic Engineering
    Item ID: 4162
    Depositing User: Dr Tomas Ward
    Date Deposited: 31 Jan 2013 14:02
    Refereed: Yes
    URI:

      Repository Staff Only(login required)

      View Item Item control page

      Downloads

      Downloads per month over past year