A New Method of EEG Classification for BCI with Feature Extraction Based on Higher Order Statistics of Wavelet Components and Selection with Genetic Algorithms.
Marcin KolodziejAndrzej MajkowskiRemigiusz J. RakPublished in: ICANNGA (1) (2011)
Keyphrases
- feature extraction
- classification accuracy
- machine learning methods
- brain computer interface
- feature set
- higher order statistics
- pairwise
- feature vectors
- extracted features
- motor imagery
- feature selection
- pattern recognition
- higher order
- unsupervised learning
- frequency domain
- probabilistic model
- correlation coefficient
- k means
- multiscale
- similarity measure