Feature Extraction for Multi-class BCI using Canonical Variates Analysis

@article{Galn2007FeatureEF,
  title={Feature Extraction for Multi-class BCI using Canonical Variates Analysis},
  author={Ferran Gal{\'a}n and P. W. Ferrez and Francesc Oliva and Joan Gu{\`a}rdia and Jose del. R. Millan},
  journal={2007 IEEE International Symposium on Intelligent Signal Processing},
  year={2007},
  pages={1-6}
}
To propose a new feature extraction method with canonical solution for multi-class brain-computer interfaces (BCI). The proposed method should provide a reduced number of canonical discriminant spatial patterns (CDSP) and rank the channels sorted by power discriminability (DP) between classes. The feature extractor relays in canonical variates analysis (CVA) which provides the CDSP between the classes. The number of CDSP is equal to the number of classes minus one. We analyze EEG data recorded… CONTINUE READING
Highly Cited
This paper has 49 citations. REVIEW CITATIONS