Paper: Yahya N, Musa H, Ong ZY, Elamvazuthi I. Classification of motor functions from electroencephalogram (EEG) signals based on an integrated method comprised of common spatial pattern and wavelet transform framework. Sensors. 2019 Jan;19(22):4878.
The Common Spatial Pattern (CSP) algorithm is an effective and popular method for classifying 2-class motor imagery electroencephalogram (EEG) data, but its effectiveness depends on the subject-specific frequency band. Is the integration of CSP and CWT optimizes the subject-specific frequency band?
Because the Common Spacial Patterns is a spatial filtering technique that reduced the dimensionality of the power feature space, and therefore it is very helpful to avoid many issues. The CSP and other data-driven spatial filters help also to get rid of the non-stationarity of the power features, making them more suitable for the majority of the classifiers.
You can check how spatial filtering can reduce non-stationarity in my recent work on Article Effect of power feature covariance shift on BCI spatial-filt...
and also talk of K.R. Müller on the topic http://videolectures.net/bbci2014_mueller_non_stationarity/
- Badges
- Science topic
- Similar topics
- Journal Impact Factor