Applying dimension reduction to EEG data by Principal Component Analysis reduces the quality of its subsequent Independent Component decomposition.
Fiorenzo ArtoniArnaud DelormeScott MakeigPublished in: NeuroImage (2018)
Keyphrases
- dimension reduction
- principal component analysis
- independent component analysis
- eeg data
- low dimensional
- linear discriminant analysis
- dimensionality reduction
- feature extraction
- random projections
- feature selection
- principal components
- singular value decomposition
- manifold learning
- high dimensional
- feature space
- dimension reduction methods
- high dimensional data
- face recognition
- brain computer interface
- unsupervised learning
- high dimensionality
- image data
- probabilistic model
- feature vectors
- human brain
- negative matrix factorization
- data analysis
- brain activity
- support vector