Time-frequency selection in two bipolar channels for improving the classification of motor imagery EEG.

Yuan Yang*, Sylvain Chevallier, Joe Wiart, Isabelle Bloch

*Corresponding author for this work

Research output: Contribution to journalArticle

10 Scopus citations

Abstract

Time and frequency information is essential to feature extraction in a motor imagery BCI, in particular for systems based on a few channels. In this paper, we propose a novel time-frequency selection method based on a criterion called Time-frequency Discrimination Factor (TFDF) to extract discriminative event-related desynchronization (ERD) features for BCI data classification. Compared to existing methods, the proposed approach generates better classification performances (mean kappa coefficient= 0.62) on experimental data from the BCI competition IV dataset IIb, with only two bipolar channels.

    Fingerprint

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this