1) In EEG Motor Imagery multiclass dataset, e.g., BCI Competition IV dataset IIa, which is a 4-class dataset (Right Hand, Left Hand, Tongue and both Feet). How can I classify the samples with the 4 classes?
2) I would like to extract spatial features using Common Spatial Pattern (CSP) from the multiclass data and give these features as input to a classifier say, SVM.
3) Is it possible to do multiclass classification using LDA as classifier?
Hi Anisa,
Well, CSP is originally defined to filter the data in a way that results in two distinct groups. But, there are one-versus-one and one-versus-rest algorithms that make this method applicable to multiclass datasets.
Similarly, LDA was originally developed for binary classification but it can be extended to handle multiclass classification.
Fatemeh
- Badges
- Science topic
- Similar topics
- Filing