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.
Original language | English (US) |
---|---|
Pages (from-to) | 2744-2747 |
Number of pages | 4 |
Journal | Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference |
DOIs | |
State | Published - Dec 1 2012 |
ASJC Scopus subject areas
- Signal Processing
- Biomedical Engineering
- Computer Vision and Pattern Recognition
- Health Informatics