Electroencephalogram (EEG) signals recorded from a persons scalp have been used to control binary cursor movements. Multiple choice paradigms will require more sophisticated protocols involving multiple mental tasks and signal representations that capture discriminatory characteristics of the EEG signals. In this study, six-channel EEG is recorded from a subject performing two mental tasks. The signals are transformed via the Karhunen-Loéve or maximum noise fraction transformations and classified by quadratic discriminant analysis. In addition, classification accuracy is tested for all subsets of the six EEG channels. Best results are approximately 90% correct when training and testing data are recorded on the same day and 75% correct when training and testing data are recorded on different days.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    EEG Subspace Representations and Feature Selection for Brain-Computer Interfaces


    Contributors:


    Publication date :

    2003-06-01


    Size :

    118251 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Incremental and robust learning of subspace representations

    Skocaj, D. / Leonardis, A. | British Library Online Contents | 2008



    Neural Decoding for Intracortical Brain-Computer Interfaces

    Dong, Yuanrui / Wang, Shirong / Huang, Qiang et al. | BASE | 2023

    Free access

    Panoramas subspace based scale invariant feature tracking method

    Zhiqiang, F. | British Library Online Contents | 2011


    Bayesian Model Selection in Nonlinear Subspace Identification

    Zhu, Rui / Fei, Qingguo / Jiang, Dong et al. | AIAA | 2022